TITLE: Implementing Semantic Search with Upstash Vector in Python
DESCRIPTION: Complete Python implementation demonstrating document indexing and semantic search using Upstash Vector. Includes environment setup, document insertion with automatic embedding generation, and similarity search functionality.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/semantic_search.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from upstash_vector import Index
from dotenv import load_dotenv
import time
# Load environment variables from a .env file
load_dotenv()
# Initialize the index from environment variables (URL and token)
index = Index.from_env()
# Example documents to be indexed
documents = [
{"id": "1", "text": "Python is a popular programming language."},
{"id": "2", "text": "Machine learning enables computers to learn from data."},
{"id": "3", "text": "Upstash provides low-latency database solutions."},
{"id": "4", "text": "Semantic search is a technique for understanding the meaning of queries."},
{"id": "5", "text": "Cloud computing allows for scalable and flexible resource management."}
]
# Reset the index to remove previous data
index.reset()
# Upsert documents into Upstash (embeddings are generated automatically)
for doc in documents:
index.upsert(
vectors=[
(doc["id"], doc["text"], {"text": doc["text"]})
]
)
print(f"Document {doc['id']} inserted.")
# Wait for the documents to be indexed
time.sleep(1)
# Search for documents similar to the query
query = "What is Python?"
results = index.query(data=query, top_k=3, include_metadata=True)
# Display search results
print("Search Results:")
for result in results:
print(f"ID: {result.id}")
print(f"Score: {result.score:.4f}")
print(f"Metadata: {result.metadata}")
print("-" * 40) # Separator line between results
```
----------------------------------------
TITLE: Server Action for Resource Creation
DESCRIPTION: Implementation of a server action to create new resources and upsert them to the vector index with input validation using Zod.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_4
LANGUAGE: typescript
CODE:
```
'use server'
import { z } from 'zod'
import { upsertEmbeddings } from '@/lib/ai/upstashVector'
const NewResourceSchema = z.object({
content: z.string().min(1),
})
export async function createResource(input: { content: string }) {
const { content } = NewResourceSchema.parse(input)
const resourceId = crypto.randomUUID()
await upsertEmbeddings(resourceId, content)
return `Resource ${resourceId} created and embedded.`
}
```
----------------------------------------
TITLE: Batch Querying Multiple Vectors in Python with Upstash
DESCRIPTION: This example shows how to perform multiple vector queries in a single API call using the query_many method. It executes two different queries with different parameters and filtering criteria, reducing round trips to the server.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/query.mdx#_snippet_1
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index
index = Index.from_env()
# Generate a random vector for similarity comparison
dimension = 128 # Adjust based on your index's dimension
query_vectors = [[random.random() for _ in range(dimension)] for _ in range(2)]
# Execute the query
query_results = index.query_many(
queries=[
{
"vector": query_vectors[0],
"include_metadata": True,
"include_data": True,
"include_vectors": False,
"top_k": 5,
"filter": "genre = 'fantasy' and title = 'Lord of the Rings'",
},
{
"vector": query_vectors[1],
"include_metadata": False,
"include_data": False,
"include_vectors": True,
"top_k": 3,
"filter": "genre = 'drama'",
},
]
)
for i, query_result in enumerate(query_results):
print(f"Query-{i} result:")
# Print the query result
for result in query_result:
print("Score:", result.score)
print("ID:", result.id)
print("Vector:", result.vector)
print("Metadata:", result.metadata)
print("Data:", result.data)
```
----------------------------------------
TITLE: Performing Semantic Search
DESCRIPTION: Code to execute a similarity search query against the vector store, returning the top 5 most relevant results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/langchain.mdx#_snippet_5
LANGUAGE: python
CODE:
```
result = store.similarity_search("Technology's role in global warming.", k=5)
print(result)
```
----------------------------------------
TITLE: Implementing LangChain with Upstash Vector Store
DESCRIPTION: Python implementation showing how to initialize Upstash Vector Store, add documents, and perform similarity search using LangChain. The code demonstrates document creation, vector store initialization with embedding enabled, and executing semantic searches.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/langchain.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from dotenv import load_dotenv
from langchain_community.vectorstores.upstash import UpstashVectorStore
from langchain.schema import Document
# Load environment variables
load_dotenv()
# Create a vector store instance
store = UpstashVectorStore(
embedding=True, # Embedding option enabled
)
# Sample documents to upload
documents = [
Document(page_content="Upstash Vector is a scalable vector database."),
Document(page_content="LangChain is a framework for building intelligent apps."),
Document(page_content="Semantic search enables advanced query matching."),
]
# Add documents to the Upstash Vector index
store.add_documents(documents)
# Perform a similarity search
query = "What is LangChain?"
results = store.similarity_search(query, k=3)
print("Similarity Search Results:")
for res in results:
print(res.page_content)
```
----------------------------------------
TITLE: Querying Upstash Vector Index
DESCRIPTION: Shows how to perform a similarity search on an Upstash Vector Index using various programming languages. The example queries for the top 3 most similar vectors to [0.6, 0.8], including metadata in the results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/overall/getstarted.mdx#_snippet_1
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(url="UPSTASH_VECTOR_REST_URL", token="UPSTASH_VECTOR_REST_TOKEN")
index.query(
vector=[0.6, 0.8],
top_k=3,
include_metadata=True,
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector";
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query({ vector: [0.6, 0.8], topK: 3, includeMetadata: true })
```
LANGUAGE: Go
CODE:
```
import "github.com/upstash/vector-go"
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Query(vector.Query{
Vector: []float32{0.6, 0.8},
TopK: 3,
IncludeMetadata: true,
})
}
```
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
$index = new Index(
url: '<UPSTASH_VECTOR_REST_URL>',
token: '<UPSTASH_VECTOR_REST_TOKEN>',
);
$index->query(new VectorQuery(
vector: [0.6, 0.8],
topK: 3,
includeMetadata: true,
));
```
LANGUAGE: Shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"vector": [0.6, 0.8], "topK": 3, "includeMetadata": "true"}'
```
----------------------------------------
TITLE: Starting a Resumable Query in JavaScript
DESCRIPTION: Shows how to initiate a resumable vector query using the Upstash Vector JavaScript SDK. The code creates an index instance and performs the initial query, returning results along with functions to fetch more results or stop the query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_1
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
});
const { result, fetchNext, stop } = await index.resumableQuery({
vector: [0.1, 0.2],
topK: 2,
includeMetadata: true,
});
// first batch of the results
for (let r of result) {
console.log(r);
}
```
----------------------------------------
TITLE: Document Querying Implementation
DESCRIPTION: Complete implementation for setting up Upstash Vector Store, creating an index, and querying parsed documents using OpenAI LLM.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/llamaparse.mdx#_snippet_4
LANGUAGE: python
CODE:
```
from llama_index.core import VectorStoreIndex
from llama_index.vector_stores.upstash import UpstashVectorStore
from llama_index.core import StorageContext
import openai
# Load environment variables for API keys and Upstash configuration
from dotenv import load_dotenv
import os
load_dotenv()
# Set up OpenAI API key
openai.api_key = os.getenv("OPENAI_API_KEY")
# Set up Upstash Vector Store
upstash_vector_store = UpstashVectorStore(
url=os.getenv("UPSTASH_VECTOR_REST_URL"),
token=os.getenv("UPSTASH_VECTOR_REST_TOKEN"),
)
# Create a storage context for Upstash Vector and index the parsed document
storage_context = StorageContext.from_defaults(vector_store=upstash_vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)
# Create a query engine for the index and perform a query
query_engine = index.as_query_engine()
query = "What are the main points discussed in the document?"
response = query_engine.query(query)
print(response)
```
----------------------------------------
TITLE: Upserting Vectors with Data and Metadata
DESCRIPTION: Demonstrates how to upsert vectors with both data and metadata fields. Shows implementation across multiple languages with examples of setting different combinations of vector values, metadata, and data fields.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_22
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
[
{
"id": "id-0",
"vector": [0.9215, 0.3897],
"metadata": {"url": "https://imgur.com/z9AVZLb"},
"data": "data-0",
},
{
"id": "id-1",
"vector": [0.3897, 0.9215],
"data": "data-1",
},
],
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert([
{
id: "id-0",
vector: [0.9215, 0.3897],
metadata: {"url": "https://imgur.com/z9AVZLb"},
data: "data-0",
},
{
id: "id-1",
vector: [0.3897, 0.9215],
data: "data-1",
},
])
```
----------------------------------------
TITLE: Querying Vector Index with Direct Vector Input in TypeScript
DESCRIPTION: Demonstrates how to query a vector index by directly providing a vector array. Includes options for retrieving metadata and vectors in a specific namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/query.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
await index.query({
topK: 2,
vector: [ ... ],
includeMetadata: true,
includeVectors: true
}, { namespace: "my-namespace" })
```
----------------------------------------
TITLE: Querying with Reciprocal Rank Fusion in Python
DESCRIPTION: Example of using RRF fusion algorithm for querying a hybrid index in Python. It demonstrates how to create an Index object and perform a query with both dense and sparse vectors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_2
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
from upstash_vector.types import FusionAlgorithm, SparseVector
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
vector=[0.5, 0.4],
sparse_vector=SparseVector([3, 5], [0.3, 0.5]),
fusion_algorithm=FusionAlgorithm.RRF,
)
```
----------------------------------------
TITLE: Querying Vector Index with Text Data in TypeScript
DESCRIPTION: Shows how to query the vector index using text data with metadata filtering. The example demonstrates searching for a movie description with specific genre and title filters.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/query.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
const results = await index.query({
data: "Movie about an adventure of a hobbit in a fantasy world.",
includeVectors: true,
includeMetadata: true,
topK: 1,
filter: "genre = 'fantasy' and title = 'Lord of the Rings'"
});
```
----------------------------------------
TITLE: Custom OpenAI Embedding Model Implementation
DESCRIPTION: Implementation using OpenAI's text-embedding-ada-002 model for custom vector embeddings, including chunking and querying functionality.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_3
LANGUAGE: typescript
CODE:
```
import { Index } from '@upstash/vector'
import { embed, embedMany } from 'ai'
import { openai } from '@ai-sdk/openai'
const index = new Index({
url: process.env.UPSTASH_VECTOR_REST_URL!,
token: process.env.UPSTASH_VECTOR_REST_TOKEN!,
})
function generateChunks(input: string): string[] {
return input
.trim()
.split('.')
.filter(i => i !== '')
}
const embeddingModel = openai.embedding('text-embedding-ada-002')
async function generateEmbedding(value: string): Promise<number[]> {
const input = value.replaceAll('\\n', ' ')
const { embedding } = await embed({
model: embeddingModel,
value: input,
})
return embedding
}
async function generateEmbeddings(value: string): Promise<Array<{ content: string; embedding: number[] }>> {
const chunks = generateChunks(value)
const { embeddings } = await embedMany({
model: embeddingModel,
values: chunks,
})
return embeddings.map((vector, i) => ({
content: chunks[i],
embedding: vector,
}))
}
export async function upsertEmbeddings(resourceId: string, content: string) {
const chunkEmbeddings = await generateEmbeddings(content)
const toUpsert = chunkEmbeddings.map((chunk, i) => ({
id: `${resourceId}-${i}`,
vector: chunk.embedding,
metadata: {
resourceId,
content: chunk.content,
},
}))
await index.upsert(toUpsert)
}
export async function findRelevantContent(query: string, k = 4) {
const userEmbedding = await generateEmbedding(query)
const result = await index.query({
vector: userEmbedding,
topK: k,
includeMetadata: true,
})
return result
}
```
----------------------------------------
TITLE: Inserting Documents into Vector Store
DESCRIPTION: Code to add processed documents to the Upstash Vector index.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/langchain.mdx#_snippet_4
LANGUAGE: python
CODE:
```
inserted_vectors = store.add_documents(docs)
```
----------------------------------------
TITLE: Querying the Vector Index
DESCRIPTION: Example showing how to create a query engine and perform queries against the vector index to retrieve information from documents.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/llamaindex.mdx#_snippet_3
LANGUAGE: python
CODE:
```
# Initialize the query engine
query_engine = index.as_query_engine()
# Perform queries
response_1 = query_engine.query("What is global warming?")
print(response_1)
response_2 = query_engine.query("How can we reduce our carbon footprint?")
print(response_2)
```
----------------------------------------
TITLE: Upserting Vectors with Metadata in JavaScript
DESCRIPTION: Code snippet showing how to upsert a vector with metadata in JavaScript. It initializes an Index object from the @upstash/vector package and adds a vector with URL metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_1
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert({
"id": "id-0",
vector: [0.9215, 0.3897],
metadata: {
url: "https://imgur.com/z9AVZLb",
},
})
```
----------------------------------------
TITLE: LlamaIndex and Upstash Vector Setup
DESCRIPTION: Initialization of LlamaIndex with Upstash Vector store, including document loading and index creation with 1536 dimensions
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/llamaindex.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.upstash import UpstashVectorStore
from llama_index.core import StorageContext
import openai
import os
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
openai.api_key = os.environ["OPENAI_API_KEY"]
# Setup the Upstash vector store
upstash_vector_store = UpstashVectorStore(
url=os.environ["UPSTASH_VECTOR_REST_URL"],
token=os.environ["UPSTASH_VECTOR_REST_TOKEN"],
)
# Read the document about global warming from the documents directory
documents = SimpleDirectoryReader("./documents/").load_data()
# Initialize the storage context with the Upstash vector store
storage_context = StorageContext.from_defaults(vector_store=upstash_vector_store)
# Create the index from the loaded document with 1536 dimensions and cosine distance
index = VectorStoreIndex.from_documents(
documents, storage_context=storage_context
)
```
----------------------------------------
TITLE: Querying Vectors with Metadata Filtering in Python
DESCRIPTION: Python implementation for querying Upstash Vector with metadata filtering. This example filters vectors by population size and geographic continent.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
vector=[0.9215, 0.3897],
filter="population >= 1000000 AND geography.continent = 'Asia'",
top_k=5,
include_metadata=True
)
```
----------------------------------------
TITLE: Querying Upstash Vector Index with Dense and Sparse Modes in JavaScript
DESCRIPTION: This snippet shows how to initialize an Upstash Vector index and perform both dense and sparse queries using JavaScript. It utilizes the @upstash/vector package and demonstrates setting up the index, executing queries, and preparing for result reranking.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_6
LANGUAGE: JavaScript
CODE:
```
import { Index, QueryMode } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
const denseResults = await index.query({
data: "Upstash Vector",
queryMode: QueryMode.DENSE,
})
const sparseResults = await index.query({
data: "Upstash Vector",
queryMode: QueryMode.SPARSE,
})
// Rerank dense and sparse results as you like here
```
----------------------------------------
TITLE: Metadata Filtering in Vector Queries
DESCRIPTION: Demonstrates how to filter vector query results based on metadata values using conditional expressions.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/query.mdx#_snippet_4
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->query(new VectorQuery(
vector: [0.1, 0.2, ...],
topK: 15,
filter: "country = 'PT' AND continent = 'EU'"
));
```
----------------------------------------
TITLE: Querying Vectors with Metadata Filtering using cURL
DESCRIPTION: A cURL command example for querying Upstash Vector with metadata filtering. This example filters vectors by population size and geographic continent.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_5
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector":[0.9215,0.3897],
"topK" : 5,
"filter": "population >= 1000000 AND geography.continent = \"Asia\"",
"includeMetadata": true
}'
```
----------------------------------------
TITLE: Upserting Vectors Using Tuples in Python
DESCRIPTION: This snippet shows how to upsert vectors into an Upstash Vector index using tuples. Each tuple contains an ID, vector array, metadata dictionary, and unstructured data. The approach is more compact than using Vector objects but provides the same functionality.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/upsert.mdx#_snippet_1
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index
index = Index.from_env()
dimension = 128 # Adjust based on your index's dimension
upsert_amount = 100
vectors = [
(
f"generated-id-{i}",
[random.random() for _ in range(dimension)],
{"some_field": f"some_value-{i}"},
f"some-unstructured-data-{i}",
)
for i in range(upsert_amount)
]
index.upsert(vectors=vectors)
```
----------------------------------------
TITLE: Basic Vector Query using cURL
DESCRIPTION: Example of a basic vector query request using cURL, demonstrating how to query vectors with metadata inclusion and topK parameter specification.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "vector": [0.1, 0.2], "topK": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Querying Upstash Vector Index with Dense and Sparse Modes in Go
DESCRIPTION: This Go code demonstrates how to create an Upstash Vector index and perform dense and sparse queries. It uses the github.com/upstash/vector-go package, showing index initialization and query execution for both query modes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_7
LANGUAGE: Go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex(
"UPSTASH_VECTOR_REST_URL",
"UPSTASH_VECTOR_REST_TOKEN",
)
denseScores, err := index.QueryData(vector.QueryData{
Data: "Upstash Vector",
QueryMode: vector.QueryModeDense,
})
sparseScores, err := index.QueryData(vector.QueryData{
Data: "Upstash Vector",
QueryMode: vector.QueryModeSparse,
})
// Rerank dense and sparse results as you like here
}
```
----------------------------------------
TITLE: Using Namespaces for Vector Operations
DESCRIPTION: Demonstrates how to perform upsert and query operations within a specific namespace. The code initializes an index connection and executes vector operations in the 'ns' namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/namespaces.mdx#_snippet_0
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
[("id-0", [0.9215, 0.3897])],
namespace="ns",
)
index.query(
[0.9215, 0.3897],
top_k=5,
namespace="ns",
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
const namespace = index.namespace("ns")
await namespace.upsert({
id: "id-0",
vector: [0.9215, 0.3897],
})
await namespace.query({
vector: [0.9215, 0.3897],
topK: 5,
})
```
----------------------------------------
TITLE: Implementing Resumable Query with Metadata Filtering in TypeScript
DESCRIPTION: This code snippet illustrates how to use the resumableQuery method with metadata filtering and type-safe metadata handling. It shows setting up a metadata type, applying a filter, and accessing typed metadata fields.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/resumable-query.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
type Metadata = {
title: string,
genre: 'sci-fi' | 'fantasy' | 'horror' | 'action'
}
const { result, fetchNext, stop } = await index.resumableQuery<Metadata>({
vector: [
... // query embedding
],
includeMetadata: true,
topK: 1,
filter: "genre = 'fantasy' and title = 'Lord of the Rings'",
maxIdle: 3600,
})
if (result[0].metadata) {
// Since we passed the Metadata type parameter above,
// we can interact with metadata fields without having to
// do any typecasting.
const { title, genre } = result[0].metadata;
console.log(`The best match in fantasy was ${title}`)
}
await stop();
```
----------------------------------------
TITLE: Single Vector Upsert Operation in TypeScript
DESCRIPTION: Demonstrates how to upsert a single vector with metadata into the vector database. The vector must match the index's dimension count.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
await index.upsert({
id: "1234",
vector: [0.1, 0.2, 0.3, 0.4, 0.5],
metadata: {
title: "Lord of The Rings",
genre: "drama",
category: "classic",
},
});
```
----------------------------------------
TITLE: Specifying Namespace for Vector Queries in Python with Upstash
DESCRIPTION: This snippet demonstrates how to specify a namespace when querying vectors from an Upstash Vector index. When no namespace is provided, the default namespace is used.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/query.mdx#_snippet_2
LANGUAGE: python
CODE:
```
index.query(..., namespace="ns")
```
----------------------------------------
TITLE: Vector-Based Similarity Search
DESCRIPTION: Implementation of similarity search using direct vector query instead of text.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/huggingface-embeddings.mdx#_snippet_5
LANGUAGE: python
CODE:
```
result_vector_query = vector_store.similarity_search_by_vector(
embedding=query_embedding,
k=5
)
print("Results for vector-based similarity search:")
for res in result_vector_query:
print(res.page_content)
```
----------------------------------------
TITLE: Querying with Embedding Models in PHP
DESCRIPTION: Shows how to query vector indexes using string data that gets automatically converted to vector embeddings using configured embedding models.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/query.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataQuery;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->queryData(new DataQuery(
data: 'What is the capital of France?',
topK: 1,
includeData: true,
));
```
----------------------------------------
TITLE: Single Data Upsert Operation in TypeScript
DESCRIPTION: Demonstrates upserting a single text data entry that will be converted to a vector embedding, including metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_4
LANGUAGE: typescript
CODE:
```
await index.upsert({
id: "1234",
data: "'The Lord of the Rings' follows Frodo Baggins and his allies on a quest to destroy a powerful ring and save Middle-earth from the dark lord Sauron.",
metadata: {
title: "Lord of The Rings",
genre: "drama",
category: "classic",
},
});
```
----------------------------------------
TITLE: Complete Resumable Query Example in Python
DESCRIPTION: A full example showing how to create an index, upsert vectors, perform a resumable query, and handle the results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_10
LANGUAGE: python
CODE:
```
from upstash_vector import Index
# Create an index instance
index = Index()
# Upsert vectors into the index
index.upsert(
vectors=[
("id1", [0.1, 0.2], {"field": "value1"}),
("id2", [0.3, 0.4], {"field": "value2"}),
("id3", [0.5, 0.6], {"field": "value3"}),
],
namespace="example-namespace"
)
# Start a resumable query
query = index.resumable_query(
vector=[0.1, 0.2],
top_k=2,
include_metadata=True,
include_vectors=True,
namespace="example-namespace"
)
# Fetch initial results
results = query.start()
# Access result data
for result in results:
print(f"ID: {result.id}, Metadata: {result.metadata}")
# Stop the query when done
query.stop()
```
----------------------------------------
TITLE: Querying with Metadata Filtering in JavaScript
DESCRIPTION: Code snippet showing how to query vectors with metadata filtering in JavaScript. It uses a filter expression to select vectors whose URL metadata matches the pattern '*imgur.com*'.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_12
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query({
vector: [0.9215, 0.3897],
topK: 5,
includeMetadata: true,
filter: "url GLOB '*imgur.com*'",
})
```
----------------------------------------
TITLE: Starting a Resumable Query in Go
DESCRIPTION: Demonstrates how to initiate a resumable vector query using the Upstash Vector Go SDK. The code creates an index and performs the initial query, returning scores, a handle for subsequent requests, and handles any potential errors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_2
LANGUAGE: go
CODE:
```
package main
import (
"fmt"
"log"
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex(
"UPSTASH_VECTOR_REST_URL",
"UPSTASH_VECTOR_REST_TOKEN",
)
scores, handle, err := index.ResumableQuery(vector.ResumableQuery{
Vector: []float32{0.1, 0.2},
TopK: 2,
IncludeMetadata: true,
})
if err != nil {
log.Fatal(err)
}
defer handle.Close()
// first batch of the results
for _, score := range scores {
fmt.Printf("%+v\n", score)
}
}
```
----------------------------------------
TITLE: Querying Vectors by Similarity in Python with Upstash
DESCRIPTION: This example demonstrates how to query vectors from an Upstash Vector index using similarity comparison. It generates a random vector, queries the index with filtering criteria, and processes the results including metadata and data.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/query.mdx#_snippet_0
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index
index = Index.from_env()
# Generate a random vector for similarity comparison
dimension = 128 # Adjust based on your index's dimension
query_vector = [random.random() for _ in range(dimension)]
# Execute the query
query_result = index.query(
vector=query_vector,
include_metadata=True,
include_data=True,
include_vectors=False,
top_k=5,
filter="genre = 'fantasy' and title = 'Lord of the Rings'",
)
# Print the query result
for result in query_result:
print("Score:", result.score)
print("ID:", result.id)
print("Vector:", result.vector)
print("Metadata:", result.metadata)
print("Data:", result.data)
```
----------------------------------------
TITLE: Upserting Text Data with Upstash Vector
DESCRIPTION: Examples of upserting raw text data into Upstash Vector database using various programming languages. The code demonstrates how to create an index instance and upsert data with metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/embeddingmodels.mdx#_snippet_0
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
[("id-0", "Upstash is a serverless data platform.", {"field": "value"})],
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert({
id: "id-0",
data: "Upstash is a serverless data platform.",
metadata: {
field: "value",
},
})
```
LANGUAGE: Go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.UpsertData(vector.UpsertData{
Id: "id-0",
Data: "Upstash is a serverless data platform.",
Metadata: map[string]any{"field": "value"},
})
}
```
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->upsertData(new DataUpsert(
id: 'id-0',
data: 'Upstash is a serverless data platform.',
metadata: [
'field' => 'value',
],
));
```
LANGUAGE: Shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert-data \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"id": "1", "data": "Upstash is a serverless data platform.", "metadata": {"field": "value"}}'
```
----------------------------------------
TITLE: Deleting Vectors by Metadata Filter in Python
DESCRIPTION: This snippet shows how to delete vectors from an Upstash Vector index based on a metadata filter. It will delete all vectors that match the specified filter condition.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/delete.mdx#_snippet_3
LANGUAGE: python
CODE:
```
index.delete(filter="age > 30")
```
----------------------------------------
TITLE: Upserting Dense and Sparse Vectors in Multiple Languages
DESCRIPTION: Examples showing how to upsert both dense and sparse vectors into an Upstash Vector index. Demonstrates initialization and vector insertion across different programming languages with proper authentication.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index, Vector
from upstash_vector.types import SparseVector
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
vectors=[
Vector(id="id-0", vector=[0.1, 0.5], sparse_vector=SparseVector([1, 2], [0.1, 0.2])),
Vector(id="id-1", vector=[0.3, 0.7], sparse_vector=SparseVector([123, 44232], [0.5, 0.4])),
]
)
```
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert([{
id: 'id-0',
vector: [0.1, 0.5],
sparseVector: {
indices: [2, 3],
values: [0.13, 0.87],
},
}])
```
----------------------------------------
TITLE: Querying vector data with curl
DESCRIPTION: Basic curl request to query vector data with topK and metadata options. Sends a text prompt to find similar vectors in the default namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query-data.mdx#_snippet_0
LANGUAGE: curl
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query-data \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "data": "What is Upstash?", "topK": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Deleting Vectors by Metadata Filter in Typescript
DESCRIPTION: Shows how to delete vectors that match specific metadata criteria using a filter expression. Note that this performs a full scan operation and may be slow for large indexes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/delete.mdx#_snippet_3
LANGUAGE: typescript
CODE:
```
const response = await index.delete({
filter: "age > 30",
});
// { deleted: 3 }
```
----------------------------------------
TITLE: Executing Resumable Query with Data Input in TypeScript
DESCRIPTION: This example shows how to use the resumableQuery method with a data input instead of a vector. It demonstrates setting query parameters, logging results, fetching additional results, and stopping the query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/resumable-query.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
const { result, fetchNext, stop } = await index.resumableQuery({
maxIdle: 3600,
topK: 50,
data: "lord of the rings"
includeMetadata: true,
includeData: true,
});
console.log(result);
/*
[{
id: '6345',
score: 1.00000012,
data: "hobbit",
metadata: {
sentence: "Upstash is great."
}
// ... more results
}]
*/
const nextBatch = await fetchNext(5); // Fetch next 5 results
console.log(nextBatch);
await stop(); // Stop the resumable query
```
----------------------------------------
TITLE: Querying Vectors with Data Inclusion
DESCRIPTION: Demonstrates how to query vectors while including their associated data in the results. Shows implementation with includeData parameter across different programming languages.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_24
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
result = index.query(
data="What is Upstash?",
include_data=True,
)
for res in result:
print(f"{res.id}: {res.data}")
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
const result = await index.query({
data: "What is Upstash?",
includeData: true,
topK: 3
})
for (const vector of result) {
console.log(`${vector.id}: ${vector.data}`)
}
```
----------------------------------------
TITLE: Starting a Resumable Query in Python
DESCRIPTION: Demonstrates how to initiate a resumable vector query using the Upstash Vector Python SDK. The code creates an index connection and performs the initial query, returning both results and a handle for subsequent requests.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
result, handle = index.resumable_query(
vector=[0.1, 0.2],
top_k=2,
include_metadata=True,
)
# first batch of the results
for r in result:
print(r)
```
----------------------------------------
TITLE: Querying Vectors with Metadata Filtering in JavaScript
DESCRIPTION: JavaScript implementation for querying Upstash Vector with metadata filtering. This example filters vectors by population size and geographic continent.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_2
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query({
vector: [0.9215, 0.3897],
filter: "population >= 1000000 AND geography.continent = 'Asia'",
topK: 5,
includeMetadata: true,
});
```
----------------------------------------
TITLE: Custom Reranking with Text Data in Python
DESCRIPTION: Shows how to perform separate queries for dense and sparse components using text data in Python. This is useful for hybrid indexes with Upstash-hosted embedding models, allowing for custom reranking of text-based queries.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_5
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
from upstash_vector.types import SparseVector, QueryMode
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
dense_results = index.query(
data="Upstash Vector",
query_mode=QueryMode.DENSE,
)
sparse_results = index.query(
data="Upstash Vector",
query_mode=QueryMode.SPARSE,
)
```
----------------------------------------
TITLE: Fetching Multiple Vectors with Included Data in Python
DESCRIPTION: This example demonstrates how to fetch multiple vectors from an index by their IDs while including vector data, metadata, and vector values in the results. It creates an Index instance from environment variables and then displays the retrieved vector information.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/fetch.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
# Specify the identifiers of vectors to be fetched
ids_to_fetch = ["id-1", "id-2", "id-3"]
# Fetch the specified vectors with vectors and metadata included
fetch_result = index.fetch(
ids=ids_to_fetch,
include_vectors=True,
include_metadata=True,
include_data=True,
)
# Display the fetched vectors
for vector_info in fetch_result:
print("ID:", vector_info.id)
print("Vector:", vector_info.vector)
print("Metadata:", vector_info.metadata)
print("Data:", vector_info.data)
```
----------------------------------------
TITLE: Weighted Queries Using IDF Strategy
DESCRIPTION: Implements weighted querying using Inverse Document Frequency (IDF) for better term importance calculation. Uses the formula IDF(qᵢ) = log((N - n(qᵢ) + 0.5) / (n(qᵢ) + 0.5)) where N is total documents and n(qᵢ) is documents containing term qᵢ.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_9
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
from upstash_vector.types import WeightingStrategy
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
data="Upstash Vector",
top_k=5,
weighting_strategy=WeightingStrategy.IDF,
)
```
----------------------------------------
TITLE: Resuming a Query in Go
DESCRIPTION: Shows how to continue a resumable query in Go by fetching additional batches of similar vectors using the handle from the initial query. The code makes multiple Next calls with different batch sizes and handles any potential errors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_6
LANGUAGE: go
CODE:
```
// next batch of the results
scores, err = handle.Next(vector.ResumableQueryNext{
AdditionalK: 3,
})
if err != nil {
log.Fatal(err)
}
for _, score := range scores {
fmt.Printf("%+v\n", score)
}
// it is possible to call Next more than once
scores, err = handle.Next(vector.ResumableQueryNext{
AdditionalK: 5,
})
if err != nil {
log.Fatal(err)
}
for _, score := range scores {
fmt.Printf("%+v\n", score)
}
```
----------------------------------------
TITLE: Querying Hybrid Vector Index in PHP
DESCRIPTION: Demonstrates querying hybrid indexes that combine both dense and sparse vectors using the Upstash Vector SDK.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/query.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
use Upstash\Vector\SparseVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->query(new VectorQuery(
vector: [0.1, 0.2, ...],
sparseVector: new SparseVector(
indices: [1, 2, 3],
values: [5.0, 6.0, 7.0],
),
topK: 15,
));
```
----------------------------------------
TITLE: Querying Hybrid Indexes with Text Data
DESCRIPTION: Examples demonstrating how to query hybrid indexes using text data with Upstash-hosted embedding models. Shows implementation across different programming languages using the query API.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
data="Upstash Vector",
top_k=5,
)
```
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query(
{
data: "Upstash Vector",
topK: 1,
},
)
```
----------------------------------------
TITLE: Creating a Resumable Query in Python
DESCRIPTION: Create a resumable query using the Index class with options for vector similarity search, including metadata, vectors, and namespace specifications.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_0
LANGUAGE: python
CODE:
```
query = index.resumable_query(
vector=[0.1, 0.2], # or use 'data' parameter for text-based queries
top_k=2,
include_metadata=True,
include_vectors=True,
namespace="your_namespace"
)
```
----------------------------------------
TITLE: Basic Vector Fetch in TypeScript
DESCRIPTION: Demonstrates how to fetch multiple vectors using an array of IDs. Returns an array of vector objects with their IDs.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/fetch.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
await index.fetch(["2", "3"]);
// [{ id: "2" }, { id: "3" }]
```
----------------------------------------
TITLE: Implementing Gradio Interface and QA Pipeline
DESCRIPTION: Setting up the Question Answering pipeline with Hugging Face and creating the Gradio interface for user interaction.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/gradio-application.mdx#_snippet_4
LANGUAGE: python
CODE:
```
# Set up a Hugging Face Question Answering model
qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
# Gradio interface function
def answer_question(query):
# Retrieve relevant documents from Upstash Vector
results = vector_store.similarity_search(query, k=3)
# Use the most relevant document for QA
if results:
context = results[0].page_content
qa_input = {"question": query, "context": context}
answer = qa_pipeline(qa_input)["answer"]
return f"Answer: {answer}\n\nContext: {context}"
else:
return "No relevant context found."
# Set up Gradio interface
iface = gr.Interface(
fn=answer_question,
inputs="text",
outputs="text",
title="RAG Application",
description="Ask a question, and the app will retrieve relevant information and provide an answer."
)
# Launch the Gradio app
iface.launch()
```
----------------------------------------
TITLE: Implementing Chat API Route with OpenAI and Upstash Vector in TypeScript
DESCRIPTION: This code snippet defines the POST route for the chat API. It uses OpenAI's GPT-4 model, implements custom tools for adding and retrieving information from a knowledge base, and handles streaming responses.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_5
LANGUAGE: typescript
CODE:
```
import { openai } from '@ai-sdk/openai'
import { streamText, tool } from 'ai'
import { z } from 'zod'
// Tools
import { createResource } from '@/lib/actions/resources'
import { findRelevantContent } from '@/lib/ai/upstashVector'
// Allow streaming responses up to 30 seconds
export const maxDuration = 30
export async function POST(req: Request) {
const { messages } = await req.json()
const result = streamText({
// 1. Choose your AI model
model: openai('gpt-4o'),
// 2. Pass along the conversation messages from the user
messages,
// 3. Prompt the model
system: `You are a helpful RAG assistant.
You have the ability to add and retrieve content from your knowledge base.
Only respond to the user with information found in your knowledge base.
If no relevant information is found, respond with: "Sorry, I don't know."`,
// 4. Provide your "tools": resource creation & retrieving content
tools: {
addResource: tool({
description: `Add new content to the knowledge base.`,
parameters: z.object({
content: z.string().describe('The content to embed and store'),
}),
execute: async ({ content }) => {
const msg = await createResource({ content })
return msg
},
}),
getInformation: tool({
description: `Retrieve relevant knowledge from your knowledge base to answer user queries.`,
parameters: z.object({
question: z.string().describe('The question to search for'),
}),
execute: async ({ question }) => {
const hits = await findRelevantContent(question)
// Return array of metadata for each chunk
// e.g. [{ id, score, metadata: { resourceId, content }}, ... ]
return hits
},
}),
},
})
// 5. Return the streaming response
return result.toDataStreamResponse()
}
```
----------------------------------------
TITLE: Upserting Vectors with Metadata in Python
DESCRIPTION: Code snippet showing how to upsert a vector with metadata in Python. It demonstrates initializing an Index object and adding a vector with an associated URL in the metadata field.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
[("id-0", [0.9215, 0.3897]), {"url": "https://imgur.com/z9AVZLb"}],
)
```
----------------------------------------
TITLE: Upserting a Single Vector in PHP
DESCRIPTION: This snippet demonstrates how to upsert a single vector into an Upstash Vector index using the PHP SDK. It initializes an Index object with your Upstash credentials and uses the upsert() method with a VectorUpsert object containing a vector ID and randomly generated vector data.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_0
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsert(new VectorUpsert(
id: '1',
vector: createRandomVector(dimensions: 1536)
));
```
----------------------------------------
TITLE: Starting a Resumable Query in Python
DESCRIPTION: Start a resumable query to retrieve the initial results set from Upstash Vector.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_1
LANGUAGE: python
CODE:
```
initial_results = query.start()
```
----------------------------------------
TITLE: Upserting Multiple Vectors with cURL in Upstash Vector Database
DESCRIPTION: This example demonstrates how to upsert multiple vectors to the default namespace using cURL. The request includes vector IDs, dense vector values, and metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/upsert.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '[
{ "id": "id-0", "vector": [0.1, 0.2], "metadata": { "link": "upstash.com" } },
{ "id": "id-1", "vector": [0.2, 0.3] }
]'
```
----------------------------------------
TITLE: Querying Vectors with Metadata Filtering in PHP
DESCRIPTION: PHP implementation for querying Upstash Vector with metadata filtering. This example filters vectors by population size and geographic continent.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_4
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->query(new VectorQuery(
vector: [0.9215, 0.3897],
topK: 5,
includeMetadata: true,
filter: "population >= 1000000 AND geography.continent = 'Asia'",
));
```
----------------------------------------
TITLE: Querying Vectors with Metadata Filtering in Go
DESCRIPTION: Go implementation for querying Upstash Vector with metadata filtering. This example filters vectors by population size and geographic continent.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_3
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Query(vector.Query{
Vector: []float32{0.9215, 0.3897},
Filter: `population >= 1000000 AND geography.continent = 'Asia'`,
TopK: 5,
IncludeMetadata: true,
})
}
```
----------------------------------------
TITLE: Upserting a Single Vector with Namespace in PHP
DESCRIPTION: This snippet shows how to upsert a vector into a specific namespace within an Upstash Vector index. It uses the namespace() method to specify the target namespace before calling upsert() with the vector data.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_1
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->upsert(new VectorUpsert(
id: '1',
vector: createRandomVector(dimensions: 1536)
));
```
----------------------------------------
TITLE: Batch Upserting Multiple Vectors with Namespace in PHP
DESCRIPTION: This snippet shows how to batch upsert multiple vectors into a specific namespace within an Upstash Vector index. It combines the namespace() method with upsertMany() to efficiently insert multiple vectors into the specified namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->upsertMany([
new VectorUpsert(
id: '1',
vector: createRandomVector(dimensions: 1536)
),
new VectorUpsert(
id: '2',
vector: createRandomVector(dimensions: 1536)
),
]);
```
----------------------------------------
TITLE: Upserting Raw Text Data
DESCRIPTION: Shows how to upsert raw text data which automatically sets the data field. The example demonstrates the process across different programming languages.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_23
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
[
{
"id": "id-2",
"data": "Upstash is a serverless data platform.",
},
],
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert([
{
id: "id-2",
data: "Upstash is a serverless data platform.",
}
])
```
----------------------------------------
TITLE: Querying with Metadata Filtering in Python
DESCRIPTION: Code snippet showing how to query vectors with metadata filtering in Python. It demonstrates using a metadata filter expression to find vectors whose URL metadata contains 'imgur.com'.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_11
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
[0.9215, 0.3897],
top_k=5,
include_metadata=True,
filter="url GLOB '*imgur.com*'",
)
```
----------------------------------------
TITLE: Document Parsing with LlamaParse
DESCRIPTION: Python code to initialize LlamaParse and parse documents using SimpleDirectoryReader. Configures the parser for markdown output and processes text files.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/llamaparse.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader
# Initialize the parser
parser = LlamaParse(result_type="markdown")
# Parse a document
file_extractor = {".txt": parser}
documents = SimpleDirectoryReader(
input_files=["./documents/global_warming.txt"],
file_extractor=file_extractor
).load_data()
```
----------------------------------------
TITLE: Querying Vectors with Metadata Retrieval in PHP
DESCRIPTION: Code snippet showing how to query vectors and include metadata in the results using PHP. It uses the VectorQuery class with includeMetadata set to true to retrieve metadata with search results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_8
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->query(new VectorQuery(
vector: [0.9215, 0.3897],
topK: 5,
includeMetadata: true,
));
```
----------------------------------------
TITLE: Updating Vector Metadata in PHP
DESCRIPTION: This snippet demonstrates how to update only metadata for an existing vector in Upstash Vector without changing the vector itself. It uses the update() method with VectorUpdate object and specifies the update mode as OVERWRITE to replace existing metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_4
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpdate;
use Upstash\Vector\Enums\UpdateMode;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->update(new VectorUpdate(
id: '1',
metadata: ['foo' => 'baz'],
metadataUpdateMode: UpdateMode::OVERWRITE,
));
```
----------------------------------------
TITLE: Specifying Namespace for Vector Upsert Operations in Python
DESCRIPTION: This snippet shows how to specify a namespace when upserting vectors to an Upstash Vector index. By providing a namespace parameter, operations can be isolated to specific namespaces. When omitted, the default namespace is used.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/upsert.mdx#_snippet_3
LANGUAGE: python
CODE:
```
index.upsert(..., namespace="ns")
```
----------------------------------------
TITLE: Performing Resumable Query with Vector Input in TypeScript
DESCRIPTION: This snippet demonstrates how to use the resumableQuery method with a vector input. It includes setting up the query parameters, logging the initial results, fetching additional results, and stopping the query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/resumable-query.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
const { result, fetchNext, stop } = await index.resumableQuery({
maxIdle: 3600,
topK: 50,
vector: [0, 1, 2, ..., 383], // 384-dimensional vector
includeMetadata: true,
includeVectors: true,
});
console.log(result);
/*
[{
id: '6345',
score: 1.00000012,
vector: [0, 1, 2, ..., 383],
metadata: {
sentence: "Upstash is great."
}
// ... more results
}]
*/
const nextBatch = await fetchNext(5); // Fetch next 5 results
console.log(nextBatch);
await stop(); // Stop the resumable query
```
----------------------------------------
TITLE: Querying Upstash Vector Index with Dense and Sparse Modes in PHP
DESCRIPTION: This PHP code illustrates how to use the Upstash Vector SDK to initialize an index and perform dense and sparse queries. It showcases the usage of the Index class, DataQuery object, and QueryMode enum for executing different types of queries.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_8
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataQuery;
use Upstash\Vector\Enums\QueryMode;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$denseResults = $index->queryData(new DataQuery(
data: 'Upstash Vector',
topK: 3,
queryMode: QueryMode::DENSE,
));
$sparseResults = $index->queryData(new DataQuery(
data: 'Upstash Vector',
topK: 3,
queryMode: QueryMode::SPARSE,
));
// Rerank dense and sparse results as you like here
```
----------------------------------------
TITLE: Text-Based Similarity Search
DESCRIPTION: Implementation of semantic search using text query to find similar documents.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/huggingface-embeddings.mdx#_snippet_4
LANGUAGE: python
CODE:
```
query_text = "What are the effects of global warming?"
query_embedding = embeddings.embed_query(query_text)
result_text_query = vector_store.similarity_search(
query=query_text,
k=5 # Number of top results to return
)
print("Results for text-based similarity search:")
for res in result_text_query:
print(res.page_content)
```
----------------------------------------
TITLE: Initializing Embeddings and Vector Store
DESCRIPTION: Setting up the Hugging Face embeddings model and Upstash Vector store with necessary imports and configurations.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/gradio-application.mdx#_snippet_2
LANGUAGE: python
CODE:
```
# Import libraries
import gradio as gr
from dotenv import load_dotenv
from langchain_huggingface.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores.upstash import UpstashVectorStore
from transformers import pipeline
from langchain.schema import Document
# Load environment variables
load_dotenv()
# Set up embeddings and Upstash Vector store
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
vector_store = UpstashVectorStore(embedding=embeddings)
```
----------------------------------------
TITLE: Listing Namespaces
DESCRIPTION: Demonstrates how to retrieve a list of all active namespaces in the vector index. The code shows the implementation across different programming languages.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/namespaces.mdx#_snippet_2
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.list_namespaces()
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.listNamespaces()
```
----------------------------------------
TITLE: Vector Fetch by Prefix in TypeScript
DESCRIPTION: Demonstrates fetching vectors using a prefix match pattern. Returns all vectors whose IDs start with the specified prefix.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/fetch.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
await index.fetch({ prefix: "test-" });
// [{ id: "test-1" }, { id: "test-2" }, { id: "test-3" }]
```
----------------------------------------
TITLE: Multiple Vectors Upsert Operation in TypeScript
DESCRIPTION: Shows how to upsert multiple vectors simultaneously into the database. Each vector can optionally include metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
await index.upsert([
{
id: "6789",
vector: [0.6, 0.7, 0.8, 0.9, 0.9],
},
{
id: "1234",
vector: [0.1, 0.2, 0.3, 0.4, 0.5],
metadata: {
title: "Lord of The Rings",
genre: "drama",
category: "classic",
},
},
]);
```
----------------------------------------
TITLE: Loading Index Client from Environment Variables
DESCRIPTION: Python code to initialize the Upstash Vector Index client by automatically loading credentials from environment variables, which is useful for maintaining security and configuration separation.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/gettingstarted.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
```
----------------------------------------
TITLE: Querying Sparse Vectors with Dimension Arrays
DESCRIPTION: Shows how to query sparse vectors using arrays of dimension indices and values. Uses inner product similarity metric for scoring. Requires dimension indices and corresponding values, with options for top-k results and metadata inclusion.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_7
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
from upstash_vector.types import SparseVector
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
sparse_vector=SparseVector([3, 5], [0.3, 0.5]),
top_k=5,
include_metadata=True,
)
```
----------------------------------------
TITLE: Querying with Text Data in Upstash Vector
DESCRIPTION: Demonstrates text-based querying using Upstash-hosted sparse embedding models. Automatically handles text embedding before query execution. Supports top-k results specification and returns similarity scores.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_8
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
data="Upstash Vector",
top_k=5,
)
```
----------------------------------------
TITLE: Scanning the Entire Index in Python
DESCRIPTION: Example showing how to scan through all vectors in the index by using pagination with cursors, processing vectors in batches.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/range.mdx#_snippet_2
LANGUAGE: python
CODE:
```
res = index.range(cursor="", limit=5)
print(res.vectors)
while res.next_cursor != "":
res = index.range(cursor=res.next_cursor, limit=10)
print(res.vectors)
```
----------------------------------------
TITLE: Vector Update Operation in TypeScript
DESCRIPTION: Shows how to update an existing vector's metadata without changing the vector values themselves.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_3
LANGUAGE: typescript
CODE:
```
await index.upsert({
id: "1234",
vector: [0.1, 0.2, 0.3, 0.4, 0.5]
metadata: {
title: "Redis"
}
})
await index.update({
id: "1234",
metadata: {
title: "QStash"
}
})
```
----------------------------------------
TITLE: Upserting Vectors Using Dictionaries in Python
DESCRIPTION: This snippet demonstrates how to upsert vectors into an Upstash Vector index using dictionaries. Each dictionary explicitly defines the 'id', 'vector', 'metadata', and 'data' keys. This approach offers more clarity about which values correspond to which fields.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/upsert.mdx#_snippet_2
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index
index = Index.from_env()
dimension = 128 # Adjust based on your index's dimension
upsert_amount = 100
vectors = [
{
"id": f"generated-id-{i}",
"vector": [random.random() for _ in range(dimension)],
"metadata": {"some_field": f"some_value-{i}"},
"data": f"some-unstructured-data-{i}",
}
for i in range(upsert_amount)
]
index.upsert(vectors=vectors)
```
----------------------------------------
TITLE: Querying Vectors with Metadata Retrieval in JavaScript
DESCRIPTION: Code snippet showing how to query vectors and include metadata in the results using JavaScript. It demonstrates using the includeMetadata option to retrieve metadata with search results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_6
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query({
vector: [0.9215, 0.3897],
topK: 5,
includeMetadata: true,
})
```
----------------------------------------
TITLE: Deleting Vectors by ID Array in Typescript
DESCRIPTION: Demonstrates how to delete multiple vectors from an index by providing an array of vector IDs. The response indicates how many vectors were successfully deleted.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/delete.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
const response = await index.delete(["2", "3"]);
// { deleted: 2 }
```
----------------------------------------
TITLE: Upserting Text Data with Upstash Vector
DESCRIPTION: Demonstrates how to upsert text data into Upstash Vector using sparse embedding models. Requires Upstash Vector REST URL and token for authentication. Returns void after inserting vectors with text data and unique IDs.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_6
LANGUAGE: Python
CODE:
```
from upstash_vector import Index, Vector
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
vectors=[
Vector(id="id-0", data="Upstash Vector provides sparse embedding models."),
Vector(id="id-1", data="You can upsert text data with these embedding models."),
]
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert([
{
id: 'id-0',
data: "Upstash Vector provides dense and sparse embedding models.",
}
])
```
----------------------------------------
TITLE: Querying Vectors with Metadata Retrieval in Go
DESCRIPTION: Code snippet demonstrating how to query vectors and include metadata in the results using Go. It specifies IncludeMetadata:true to retrieve metadata alongside vector search results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_7
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Query(vector.Query{
Vector: []float32{0.9215, 0.3897},
TopK: 5,
IncludeMetadata: true,
})
}
```
----------------------------------------
TITLE: Querying Vectors with Metadata Retrieval in Python
DESCRIPTION: Code snippet showing how to query vectors and include metadata in the results using Python. It demonstrates setting the include_metadata flag to retrieve metadata alongside vector search results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_5
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
[0.9215, 0.3897],
top_k=5,
include_metadata=True,
)
```
----------------------------------------
TITLE: Batch Upserting Multiple Data Entries in PHP
DESCRIPTION: Demonstrates how to efficiently upsert multiple data entries at once using upsertDataMany(). Recommended for batches up to 1,000 records for optimal performance.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-data.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsertDataMany([
new DataUpsert(id: '1', data: 'The capital of Japan is Tokyo'),
new DataUpsert(id: '2', data: 'The capital of France is Paris'),
new DataUpsert(id: '3', data: 'The capital of Germany is Berlin'),
]);
```
----------------------------------------
TITLE: Querying Sparse Vector Index in PHP
DESCRIPTION: Shows how to query sparse vector indexes using SparseVector objects with specific indices and values through the Upstash Vector SDK.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/query.mdx#_snippet_1
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
use Upstash\Vector\SparseVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->query(new VectorQuery(
sparseVector: new SparseVector(
indices: [1, 2, 3],
values: [5.0, 6.0, 7.0],
),
topK: 15,
));
```
----------------------------------------
TITLE: Upserting to a Sparse Index in PHP
DESCRIPTION: This snippet demonstrates how to upsert vector data into a sparse index in Upstash Vector. It uses the SparseVector class to specify the indices and corresponding values, which is required for sparse indexes that store only non-zero vector elements.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_6
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use Upstash\Vector\SparseVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsert(new VectorUpsert(
id: '1',
sparseVector: new SparseVector(
indices: [0, 1],
values: [1.0, 2.0],
),
));
```
----------------------------------------
TITLE: Fetching Vectors Using cURL
DESCRIPTION: Example of how to fetch vectors from the default namespace using cURL with authentication. The request includes the vector ID and specifies that metadata should be included in the response.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/fetch.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/fetch \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "ids": ["id-0"], "includeMetadata": true }'
```
----------------------------------------
TITLE: Fetching Vectors by ID Prefix with Namespace in PHP
DESCRIPTION: Shows how to fetch vectors by ID prefix within a specific namespace, combining prefix matching with namespace isolation for more organized data retrieval.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/fetch.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorFetchByPrefix;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->namespace('my-namespace')->fetch(new VectorFetchByPrefix(
prefix: 'users:',
includeMetadata: true,
includeVectors: true,
includeData: true,
));
```
----------------------------------------
TITLE: Fetching Vectors from a Specific Namespace Using cURL
DESCRIPTION: Example of how to fetch vectors from a specific namespace ('ns') using cURL with authentication. The request includes multiple vector IDs and specifies that metadata should be included in the response.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/fetch.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/fetch/ns \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "ids": ["id-0", "id-1"], "includeMetadata": true }'
```
----------------------------------------
TITLE: Querying with Metadata Filtering in Go
DESCRIPTION: Code snippet demonstrating how to query vectors with metadata filtering in Go. It uses a Filter parameter with a GLOB pattern to match URLs containing 'imgur.com'.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_13
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Query(vector.Query{
Vector: []float32{0.9215, 0.3897},
TopK: 5,
IncludeMetadata: true,
Filter: "url GLOB '*imgur.com*'",
})
}
```
----------------------------------------
TITLE: Querying with Metadata Filtering in PHP
DESCRIPTION: Code snippet showing how to query vectors with metadata filtering in PHP. It passes a filter expression to the VectorQuery to select vectors with URLs containing 'imgur.com'.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_14
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorQuery;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->query(new VectorQuery(
vector: [0.9215, 0.3897],
topK: 5,
includeMetadata: true,
filter: "url GLOB '*imgur.com*'",
));
```
----------------------------------------
TITLE: Executing Basic Range Query in TypeScript
DESCRIPTION: Demonstrates a basic range query to retrieve vectors with metadata, specifying a cursor, limit, and namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/range.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
const responseRange = await index.range(
{
cursor: 0,
limit: 2,
includeMetadata: true,
},
{ namespace: "my-namespace" }
);
```
----------------------------------------
TITLE: Document Embedding and Storage
DESCRIPTION: Process for creating sample documents, embedding them using Hugging Face, and storing in Upstash Vector with batching support.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/huggingface-embeddings.mdx#_snippet_3
LANGUAGE: python
CODE:
```
from langchain.schema import Document
documents = [
Document(page_content="Global warming is causing sea levels to rise."),
Document(page_content="Artificial intelligence is transforming many industries."),
Document(page_content="Renewable energy is vital for sustainable development.")
]
vector_store.add_documents(
documents=documents,
batch_size=100,
embedding_chunk_size=200
)
print("Documents with embeddings have been stored in Upstash Vector.")
```
----------------------------------------
TITLE: Patching Metadata in Upstash Vector with JSON Merge Patch Algorithm
DESCRIPTION: Example demonstrating how to patch metadata in Upstash Vector using the JSON Merge Patch algorithm. This approach allows updating specific fields, adding new fields, or deleting existing fields by setting them to None.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/update.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index
from upstash_vector.types import MetadataUpdateMode
index = Index.from_env()
updated = index.update(
id="id2",
metadata={
"existing-field": "new-value",
"existing-field-to-delete": None,
"new-field": "new-value",
},
metadata_update_mode=MetadataUpdateMode.PATCH,
)
print(updated)
```
----------------------------------------
TITLE: Upserting Sparse Vectors in Python
DESCRIPTION: Example of upserting sparse vectors to an Upstash Vector index in Python using the upstash_vector library. It demonstrates creating sparse vectors with dimension indices and their corresponding values.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index, Vector
from upstash_vector.types import SparseVector
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.upsert(
vectors=[
Vector(id="id-0", sparse_vector=SparseVector([1, 2], [0.1, 0.2])),
Vector(id="id-1", sparse_vector=SparseVector([123, 44232], [0.5, 0.4])),
]
)
```
----------------------------------------
TITLE: Stopping a Resumable Query in JavaScript
DESCRIPTION: Shows how to properly terminate a resumable query in JavaScript to free up server resources. This should be called when you no longer need to fetch additional results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_9
LANGUAGE: javascript
CODE:
```
await stop();
```
----------------------------------------
TITLE: Retrieving Range of Vectors with Metadata using curl
DESCRIPTION: Code snippet demonstrating how to retrieve a range of vectors with metadata using curl. It sends a request to the range endpoint with cursor pagination and includeMetadata parameter.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_20
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/range \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "cursor" : "0", "limit" : 3, "includeMetadata": true}'
```
----------------------------------------
TITLE: Batch querying multiple vector queries
DESCRIPTION: Example of sending multiple query requests in a single API call, allowing for more efficient processing of several text inputs with different parameters.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query-data.mdx#_snippet_2
LANGUAGE: curl
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query-data \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '[\n {\n "data": "What is Upstash?",\n "topK": 2,\n "includeMetadata": true\n },\n {\n "data": "What is Upstash Vector?",\n "topK": 3\n }\n ]'
```
----------------------------------------
TITLE: Querying with Distribution-Based Score Fusion in JavaScript
DESCRIPTION: Example of using DBSF fusion algorithm for querying a hybrid index in JavaScript. It shows how to create an Index instance and perform a query with both dense and sparse vectors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_3
LANGUAGE: JavaScript
CODE:
```
import { FusionAlgorithm, Index } from "@upstash/vector";
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
});
await index.query({
vector: [0.5, 0.4],
sparseVector: {
indices: [2, 3],
values: [0.13, 0.87],
},
fusionAlgorithm: FusionAlgorithm.DBSF,
topK: 3,
});
```
----------------------------------------
TITLE: Upserting Sparse Vectors in JavaScript
DESCRIPTION: Example of upserting sparse vectors to an Upstash Vector index in JavaScript using the @upstash/vector library. It shows how to create a sparse vector by specifying indices and their corresponding values.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_2
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert([{
id: 'id-0',
sparseVector: {
indices: [2, 3],
values: [0.13, 0.87],
},
}])
```
----------------------------------------
TITLE: Data Update Operation in TypeScript
DESCRIPTION: Demonstrates how to update existing data entries with new metadata while maintaining the same ID.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_6
LANGUAGE: typescript
CODE:
```
await index.upsert({
id: "1234",
data: "Upstash product"
metadata: {
title: "Redis"
}
})
await index.upsert({
id: "1234",
metadata: {
title: "QStash"
}
})
```
----------------------------------------
TITLE: Batch Vector Query using cURL
DESCRIPTION: Example of a batch query request using cURL, showing how to send multiple vector queries in a single request with different parameters.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query.mdx#_snippet_2
LANGUAGE: sh
CODE:
```
curl "$UPSTASH_VECTOR_REST_URL/query" \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '[
{
"vector": [0.1, 0.2],
"topK": 2,
"includeMetadata": true
},
{
"vector": [0.2, 0.3],
"topK": 3
}
]'
```
----------------------------------------
TITLE: Upstash Vector Implementation with Hosted Embedding Models
DESCRIPTION: Implementation of vector storage and retrieval using Upstash's hosted embedding models, including chunking logic and querying functionality.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
import { Index } from '@upstash/vector'
const index = new Index({
url: process.env.UPSTASH_VECTOR_REST_URL!,
token: process.env.UPSTASH_VECTOR_REST_TOKEN!,
})
function generateChunks(input: string): string[] {
return input
.trim()
.split('.')
.filter(i => i !== '')
}
export async function upsertEmbedding(resourceId: string, content: string) {
const chunks = generateChunks(content)
const toUpsert = chunks.map((chunk, i) => ({
id: `${resourceId}-${i}`,
data: chunk,
metadata: {
resourceId,
content: chunk,
},
}))
await index.upsert(toUpsert)
}
export async function findRelevantContent(query: string, k = 4) {
const result = await index.query({
data: query,
topK: k,
includeMetadata: true,
})
return result
}
```
----------------------------------------
TITLE: Starting a Resumable Query using REST API with curl
DESCRIPTION: Shows how to initiate a resumable vector query using direct REST API calls with curl. The request includes the target vector, topK value, and configuration to include metadata in the response.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_3
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector": [0.1, 0.2],
"topK": 2,
"includeMetadata": true
}'
```
----------------------------------------
TITLE: Deleting Vectors by ID Prefix with Namespace in PHP
DESCRIPTION: This snippet shows how to delete vectors by ID prefix within a specific namespace using the Upstash Vector SDK in PHP. It combines the namespace() method with VectorDeleteByPrefix for targeted deletion.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/delete-vectors.mdx#_snippet_3
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorDeleteByPrefix;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->delete(new VectorDeleteByPrefix(
prefix: 'users:',
));
```
----------------------------------------
TITLE: Performing Resumable Vector Query with Namespace using curl
DESCRIPTION: Example of making a resumable vector query request to a specific namespace in the Upstash Vector API using curl. The request targets the 'ns' namespace with the same parameters as the default query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/resumable-query/start-with-vector.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector": [0.1, 0.2],
"topK": 2,
"includeMetadata": true,
"maxIdle": 3600
}'
```
----------------------------------------
TITLE: Fetching Vectors from a Specific Namespace with cURL
DESCRIPTION: HTTP request to range over vectors from a specific namespace 'ns', starting with cursor 0, limiting to 2 results per page, and including metadata in the response.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/range.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/range/ns \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "cursor": "0", "limit": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Resetting a Specific Namespace in Upstash Vector Using Python
DESCRIPTION: This example shows how to reset a specific namespace in an Upstash Vector index. It initializes an Index instance and calls the reset method with a namespace parameter to clear all vectors and metadata from that particular namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/reset.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
index.reset(namespace="ns")
```
----------------------------------------
TITLE: Querying Upstash Vector Index with Dense and Sparse Modes using curl
DESCRIPTION: This curl command example shows how to perform dense and sparse queries against an Upstash Vector index using RESTful API calls. It demonstrates the necessary headers and payload structure for both query modes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_9
LANGUAGE: Shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query-data \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"data": "Upstash Vector", "queryMode": "DENSE"}'
curl $UPSTASH_VECTOR_REST_URL/query-data \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"data": "Upstash Vector", "queryMode": "SPARSE"}'
```
----------------------------------------
TITLE: Deleting Vectors by ID Prefix in PHP
DESCRIPTION: This example illustrates how to delete vectors using an ID prefix with the Upstash Vector SDK in PHP. It uses the VectorDeleteByPrefix class to remove all vectors with IDs starting with a specified prefix.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/delete-vectors.mdx#_snippet_2
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorDeleteByPrefix;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->delete(new VectorDeleteByPrefix(
prefix: 'users:',
));
```
----------------------------------------
TITLE: Deleting Vectors by ID Using cURL in Upstash Vector API
DESCRIPTION: Shows how to delete specific vectors by their IDs using a cURL request to the Upstash Vector API. The request includes authentication via bearer token and specifies the vector IDs to delete in the request body.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/delete.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/delete \
-X DELETE \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "ids": [ "id-0", "id-1" ] }'
```
----------------------------------------
TITLE: Resetting Default Namespace in TypeScript
DESCRIPTION: Demonstrates how to reset the default namespace of a vector index using the basic reset method without arguments. Returns 'Successful' on successful reset.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/reset.mdx#_snippet_0
LANGUAGE: typescript
CODE:
```
const responseReset = await index.reset();
// 'Successful'
```
----------------------------------------
TITLE: Deleting Multiple Vectors by IDs in Python
DESCRIPTION: This snippet demonstrates how to delete multiple vectors from an Upstash Vector index by specifying their IDs. It creates an index connection using environment variables and deletes vectors with specific IDs.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/delete.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
# Specify the identifiers of vectors to be deleted
ids_to_delete = ["id1", "id2", "id3"]
# Delete the specified vectors
delete_result = index.delete(ids=ids_to_delete)
# Display the number of vectors deleted
print("Number of Vectors Deleted:", delete_result.deleted)
```
----------------------------------------
TITLE: Resuming a Query using REST API with curl
DESCRIPTION: Shows how to continue a resumable query using direct REST API calls with curl. The request includes a UUID to identify the query session and the number of additional results to fetch.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_7
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query-next \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"uuid": "550e8400-e29b-41d4-a716-446655440000",
"additionalK": 3
}'
```
----------------------------------------
TITLE: Fetching All Results with a Resumable Query in Python
DESCRIPTION: Implement a pattern to fetch all available results using a resumable query with batching.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_9
LANGUAGE: python
CODE:
```
query = index.resumable_query(
vector=[0.1, 0.2],
top_k=2,
include_metadata=True
)
results = query.start()
while True:
next_batch = query.fetch_next(2)
if not next_batch:
break
results.extend(next_batch)
query.stop()
```
----------------------------------------
TITLE: Fetching Vectors by ID Prefix in Python
DESCRIPTION: This snippet shows how to fetch all vectors with IDs that start with a specific prefix. It's useful for retrieving groups of related vectors but should be used with caution for larger datasets where pagination might be more appropriate.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/fetch.mdx#_snippet_3
LANGUAGE: python
CODE:
```
index.fetch(prefix="id-")
```
----------------------------------------
TITLE: Deleting Vectors by ID in PHP
DESCRIPTION: This snippet demonstrates how to delete vectors by their IDs using the Upstash Vector SDK in PHP. It initializes an Index object with the required URL and token, then uses the delete() method to remove vectors with specific IDs.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/delete-vectors.mdx#_snippet_0
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->delete(['1', '2', '3']);
```
----------------------------------------
TITLE: Querying with Metadata Filtering using curl
DESCRIPTION: Code snippet demonstrating how to query vectors with metadata filtering using curl. It sends a request with a filter parameter that uses a GLOB pattern to match URLs containing 'imgur.com'.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_15
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector":[0.9215,0.3897],
"topK" : 5,
"includeMetadata": true,
"filter": "url GLOB \"*imgur.com*\""
}'
```
----------------------------------------
TITLE: Upserting Sparse Vectors in Go
DESCRIPTION: Example of upserting sparse vectors to an Upstash Vector index in Go using the vector-go library. It demonstrates creating multiple sparse vectors with dimension indices and their corresponding values.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_3
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex(
"UPSTASH_VECTOR_REST_URL",
"UPSTASH_VECTOR_REST_TOKEN",
)
err := index.UpsertMany([]vector.Upsert{
{
Id: "id-0",
SparseVector: &vector.SparseVector{
Indices: []int32{1, 2},
Values: []float32{0.1, 0.2},
},
},
{
Id: "id-1",
SparseVector: &vector.SparseVector{
Indices: []int32{123, 44232},
Values: []float32{0.5, 0.4},
},
},
})
}
```
----------------------------------------
TITLE: Deleting a Vector with Namespace Specification in Python
DESCRIPTION: This snippet demonstrates how to delete a vector from a specific namespace in an Upstash Vector index. When no namespace is provided, the default namespace is used.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/delete.mdx#_snippet_2
LANGUAGE: python
CODE:
```
index.delete("id-4", namespace="ns")
```
----------------------------------------
TITLE: Deleting Namespaces
DESCRIPTION: Shows how to delete a specific namespace using different programming languages. The code connects to the vector index and removes the specified namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/namespaces.mdx#_snippet_1
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.delete_namespace("ns")
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.deleteNamespace("ns")
```
----------------------------------------
TITLE: Filtering Vectors by ID Prefix in Python
DESCRIPTION: Example demonstrating how to filter vectors by ID prefix, which retrieves all vectors with IDs starting with the specified prefix.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/range.mdx#_snippet_1
LANGUAGE: python
CODE:
```
index.range(prefix="id-")
```
----------------------------------------
TITLE: Upserting Single Data Entry in PHP
DESCRIPTION: Demonstrates how to upsert a single piece of data using Upstash Vector's embedding models. Uses the Index class to establish connection and DataUpsert for data insertion.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-data.mdx#_snippet_0
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsertData(new DataUpsert(
id: '1',
data: 'The capital of Japan is Tokyo',
));
```
----------------------------------------
TITLE: Type-Safe Vector Querying in TypeScript
DESCRIPTION: Illustrates how to implement type-safe querying using TypeScript generics. Includes custom metadata type definition and type-safe metadata access in the query results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/query.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
type Metadata = {
title: string,
genre: 'sci-fi' | 'fantasy' | 'horror' | 'action'
}
const results = await index.query<Metadata>({
vector: [
... // query embedding
],
includeVectors: true,
topK: 1,
filter: "genre = 'fantasy' and title = 'Lord of the Rings'"
})
if (results[0].metadata) {
const { title, genre } = results[0].metadata;
console.log(`The best match in fantasy was ${title}`)
}
```
----------------------------------------
TITLE: Resuming a Query in Python
DESCRIPTION: Shows how to continue a resumable query in Python by fetching additional batches of similar vectors using the handle from the initial query. The example demonstrates multiple calls to fetch_next with different batch sizes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_4
LANGUAGE: python
CODE:
```
# next batch of the results
next_result = handle.fetch_next(
additional_k=3,
)
for r in next_result:
print(r)
# it is possible to call fetch_next more than once
next_result = handle.fetch_next(
additional_k=5,
)
for r in next_result:
print(r)
```
----------------------------------------
TITLE: Querying Vectors with Metadata Retrieval using curl
DESCRIPTION: Code snippet demonstrating how to query vectors and include metadata in the results using curl. It sends a POST request to the query endpoint with includeMetadata set to true in the JSON payload.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_9
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector":[0.9215,0.3897],
"topK" : 5,
"includeMetadata": true
}'
```
----------------------------------------
TITLE: Initializing Hugging Face and Upstash Vector
DESCRIPTION: Setup code for loading environment variables and initializing Hugging Face embeddings model with Upstash Vector store.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/huggingface-embeddings.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from dotenv import load_dotenv
import os
load_dotenv()
from langchain_huggingface.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores.upstash import UpstashVectorStore
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
vector_store = UpstashVectorStore(embedding=embeddings)
```
----------------------------------------
TITLE: Deleting Vectors by Metadata Filter in PHP
DESCRIPTION: This code demonstrates how to delete vectors based on a metadata filter using the Upstash Vector SDK in PHP. It utilizes the VectorDeleteByMetadataFilter class to remove vectors that match a specific condition.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/delete-vectors.mdx#_snippet_4
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorDeleteByMetadataFilter;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->delete(new VectorDeleteByMetadataFilter(
filter: 'salary > 1000',
));
```
----------------------------------------
TITLE: Stopping a Resumable Query in Python
DESCRIPTION: Demonstrates how to properly terminate a resumable query in Python to free up server resources. This should be called when you no longer need to fetch additional results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_8
LANGUAGE: python
CODE:
```
handle.stop()
```
----------------------------------------
TITLE: Initializing Upstash Vector Store
DESCRIPTION: Python code to load environment variables and initialize the Upstash Vector store with automatic embedding generation.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/langchain.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from dotenv import load_dotenv
from langchain_community.vectorstores.upstash import UpstashVectorStore
load_dotenv()
# Create a vector store instance where embeddings are generated by Upstash
store = UpstashVectorStore(embedding=True)
```
----------------------------------------
TITLE: Querying Vectors with ID Prefix in TypeScript
DESCRIPTION: Shows how to use the range method to retrieve vectors with IDs starting with a specific prefix.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/range.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
const responseRange = await index.range({
cursor: 0,
limit: 2,
prefix: "test-",
});
```
----------------------------------------
TITLE: Upsert Multiple Vectors in Upstash Vector using curl
DESCRIPTION: A curl example that demonstrates how to upsert multiple vectors with text data to be embedded in the default namespace. The request includes both required fields (id, data) and optional metadata for each vector.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/upsert-data.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert-data \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '[
{ "id": "id-0", "data": "Upstash is a serverless data platform.", "metadata": { "link": "upstash.com" } },
{ "id": "id-1", "data": "Upstash Vector is a serverless vector database." }
]'
```
----------------------------------------
TITLE: Document Embedding and Storage
DESCRIPTION: Creating and storing sample documents in Upstash Vector with batching configuration for efficient processing.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/gradio-application.mdx#_snippet_3
LANGUAGE: python
CODE:
```
# Sample documents to embed and store
documents = [
Document(page_content="Global warming is causing sea levels to rise."),
Document(page_content="AI is transforming many industries."),
Document(page_content="Renewable energy is vital for sustainable development.")
]
vector_store.add_documents(documents=documents, batch_size=100, embedding_chunk_size=200)
```
----------------------------------------
TITLE: Stopping a Resumable Query in Go
DESCRIPTION: Demonstrates how to properly terminate a resumable query in Go to free up server resources. This should be called when you no longer need to fetch additional results.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_10
LANGUAGE: go
CODE:
```
handle.Close()
```
----------------------------------------
TITLE: Inserting Data into Upstash Vector Index
DESCRIPTION: Demonstrates how to insert a vector with metadata into an Upstash Vector Index using various programming languages. The example shows inserting a 2-dimensional vector with an associated ID and metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/overall/getstarted.mdx#_snippet_0
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(url="UPSTASH_VECTOR_REST_URL", token="UPSTASH_VECTOR_REST_TOKEN")
index.upsert(
vectors=[
("1", [0.6, 0.8], {"field": "value"}),
]
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector";
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.upsert({ id: "1", vector: [0.6, 0.8], metadata: {field: "value"} })
```
LANGUAGE: Go
CODE:
```
import "github.com/upstash/vector-go"
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Upsert(vector.Upsert{
Id: "1",
Vector: []float32{0.6, 0.8},
Metadata: map[string]any{"field": "value"},
})
}
```
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->upsert(new VectorUpsert(
id: '1',
vector: [0.6, 0.8],
metadata: ['field' => 'value'],
));
```
LANGUAGE: Shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"id": "1", "vector": [0.6, 0.8], "metadata": {"field": "value"}}'
```
----------------------------------------
TITLE: Resuming a Query in JavaScript
DESCRIPTION: Demonstrates continuing a resumable query in JavaScript by fetching additional batches of similar vectors using the fetchNext function from the initial query. The example shows multiple calls to fetch more results with different batch sizes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_5
LANGUAGE: javascript
CODE:
```
// next batch of the results
let nextResult = await fetchNext(3);
for (let r of nextResult) {
console.log(r);
}
// it is possible to call fetch_next more than once
nextResult = await fetchNext(3);
for (let r of nextResult) {
console.log(r);
}
```
----------------------------------------
TITLE: Retrieving Range of Vectors with Metadata in Go
DESCRIPTION: Code snippet demonstrating how to retrieve a range of vectors with metadata in Go. It uses the Range method with cursor pagination and IncludeMetadata option to fetch metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_18
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Range(vector.Range{
Cursor: "0",
Limit: 3,
IncludeMetadata: true,
})
}
```
----------------------------------------
TITLE: Retrieving Range of Vectors with Metadata in PHP
DESCRIPTION: Code snippet showing how to retrieve a range of vectors with metadata in PHP. It uses the VectorRange class with includeMetadata parameter to fetch metadata with the vectors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_19
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorRange;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->range(new VectorRange(
limit: 3,
includeMetadata: true,
));
```
----------------------------------------
TITLE: Retrieving Range of Vectors with Metadata in JavaScript
DESCRIPTION: Code snippet showing how to retrieve a range of vectors with metadata in JavaScript. It uses the range method with cursor pagination and the includeMetadata option.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_17
LANGUAGE: javascript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.range({
cursor: "0",
limit: 3,
includeMetadata: true,
})
```
----------------------------------------
TITLE: Upsert Single Vector with Custom Namespace in Upstash Vector using curl
DESCRIPTION: A curl command that demonstrates upserting a single vector with text data to a custom namespace called 'ns'. The request includes the vector's ID, the raw text to be embedded, and custom metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/upsert-data.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert-data/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "id": "id-2", "data": "Upstash is a serverless data platform.", "metadata": { "link": "upstash.com" } }'
```
----------------------------------------
TITLE: Initializing LlamaIndex with Upstash Vector Store
DESCRIPTION: Python code to initialize LlamaIndex with Upstash Vector store, load documents, and create a vector index. Includes environment setup and document processing.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/llamaindex.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.upstash import UpstashVectorStore
from llama_index.core import StorageContext
import os
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
# Set OpenAI API key
openai.api_key = os.environ["OPENAI_API_KEY"]
# Initialize Upstash Vector store
upstash_vector_store = UpstashVectorStore(
url=os.environ["UPSTASH_VECTOR_REST_URL"],
token=os.environ["UPSTASH_VECTOR_REST_TOKEN"],
)
# Load documents using SimpleDirectoryReader
documents = SimpleDirectoryReader("./documents/").load_data()
# Create a storage context and initialize the index
storage_context = StorageContext.from_defaults(vector_store=upstash_vector_store)
index = VectorStoreIndex.from_documents(
documents, storage_context=storage_context
)
```
----------------------------------------
TITLE: Upserting Vectors with Metadata in Go
DESCRIPTION: Code snippet demonstrating how to upsert a vector with metadata in Go. It creates an Index instance and adds a vector with URL metadata using the Upsert method.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_2
LANGUAGE: go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.Upsert(vector.Upsert{
Id: "id-0",
Vector: []float32{0.9215, 0.3897},
Metadata: map[string]any{"url": "https://imgur.com/z9AVZLb"},
})
}
```
----------------------------------------
TITLE: Updating Vector Metadata with Namespace in PHP
DESCRIPTION: This snippet shows how to update metadata for a vector in a specific namespace within an Upstash Vector index. It combines the namespace() method with update() to modify metadata for a vector in the specified namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_5
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpdate;
use Upstash\Vector\Enums\UpdateMode;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->update(new VectorUpdate(
id: '1',
metadata: ['foo' => 'baz'],
metadataUpdateMode: UpdateMode::OVERWRITE,
));
```
----------------------------------------
TITLE: Upserting Vectors with Metadata in PHP
DESCRIPTION: Code snippet showing how to upsert a vector with metadata in PHP. It initializes an Index object and uses the VectorUpsert class to add a vector with URL metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->upsert(new VectorUpsert(
id: 'id-0',
vector: createRandomVector(384),
metadata: [
'url' => "https://imgur.com/z9AVZLb",
],
));
```
----------------------------------------
TITLE: Stopping a Resumable Query using REST API with curl
DESCRIPTION: Shows how to properly terminate a resumable query using direct REST API calls with curl. The request includes a UUID to identify the query session that should be stopped.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_11
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query-end \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"uuid": "550e8400-e29b-41d4-a716-446655440000"
}'
```
----------------------------------------
TITLE: Upserting Single Data Entry with Namespace in PHP
DESCRIPTION: Shows how to upsert data within a specific namespace using Upstash Vector. This allows for better organization and segregation of vector data.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-data.mdx#_snippet_1
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->upsertData(new DataUpsert(
id: '1',
data: 'The capital of Japan is Tokyo',
));
```
----------------------------------------
TITLE: Performing Resumable Vector Query with curl
DESCRIPTION: Example of making a resumable vector query request to the Upstash Vector API using curl. This request includes a 2-dimensional query vector, requesting the top 2 results with metadata included and a maximum idle time of 3600 seconds.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/resumable-query/start-with-vector.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector": [0.1, 0.2],
"topK": 2,
"includeMetadata": true,
"maxIdle": 3600
}'
```
----------------------------------------
TITLE: Setting Custom Max Idle Time in JavaScript
DESCRIPTION: Demonstrates how to configure the maximum idle time for a resumable query in JavaScript. This determines how long a query can remain inactive before being automatically terminated by the server.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_13
LANGUAGE: javascript
CODE:
```
const { result, fetchNext, stop } = await index.resumableQuery({
vector: [0.1, 0.2],
topK: 2,
includeMetadata: true,
maxIdle: 7200, // two hours, in seconds
});
```
----------------------------------------
TITLE: Fetching Vectors by ID Prefix in PHP
DESCRIPTION: Demonstrates how to fetch vectors by matching their ID prefixes. This is useful for retrieving groups of related vectors that share a common ID prefix pattern.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/fetch.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorFetchByPrefix;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$results = $index->fetch(new VectorFetchByPrefix(
prefix: 'users:',
includeMetadata: true,
includeVectors: true,
includeData: true,
));
```
----------------------------------------
TITLE: Query Results Example
DESCRIPTION: Sample output from running a similarity search query, showing how results are ordered by relevance to the input query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/langchain.mdx#_snippet_2
LANGUAGE: plaintext
CODE:
```
Similarity Search Results:
LangChain is a framework for building intelligent apps.
Semantic search enables advanced query matching.
Upstash Vector is a scalable vector database.
```
----------------------------------------
TITLE: Namespace Vector Upsert Operation in TypeScript
DESCRIPTION: Demonstrates upserting vectors into a specific namespace. Namespaces allow for logical separation of vectors within the same index.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
await index.upsert([
{
id: "6789",
vector: [0.6, 0.7, 0.8, 0.9, 0.9],
},
], { namespace: "my-namespace" });
```
----------------------------------------
TITLE: Accessing Index Information Properties in PHP
DESCRIPTION: This snippet shows how to access various properties of the IndexInfo object returned by getInfo(). It includes vector counts, index size, dimensions, similarity function, and namespace information.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/info.mdx#_snippet_1
LANGUAGE: php
CODE:
```
// To know the number of vectors ready to query.
$info->vectorCount;
// To know the number of vectors that are getting indexed.
$info->pendingVectorCount;
// To know the size of the index in bytes.
$info->indexSize;
// To know the dimensions of your vector index.
$info->dimension;
// To know which similarity function is being used.
$info->similarityFunction;
// To get information about a specific index you can (More on next section):
$namespaceInfo = $info->namespace('my-namespace');
```
----------------------------------------
TITLE: Querying Content with Upstash Vector
DESCRIPTION: Python implementation for indexing parsed documents in Upstash Vector and performing semantic queries. Includes environment setup, vector store initialization, and query execution.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/llamaparse.mdx#_snippet_3
LANGUAGE: python
CODE:
```
from llama_index.core import VectorStoreIndex
from llama_index.vector_stores.upstash import UpstashVectorStore
from llama_index.core import StorageContext
from dotenv import load_dotenv
import os
# Load environment variables
load_dotenv()
# Set up Upstash Vector Store
vector_store = UpstashVectorStore(
url=os.getenv("UPSTASH_VECTOR_REST_URL"),
token=os.getenv("UPSTASH_VECTOR_REST_TOKEN")
)
# Create storage context and index the parsed document
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)
# Perform a query
query_engine = index.as_query_engine()
response = query_engine.query("What is the main topic discussed in the document?")
```
----------------------------------------
TITLE: Stopping an Async Resumable Query in Python
DESCRIPTION: Stop an asynchronous resumable query to release server-side resources.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_7
LANGUAGE: python
CODE:
```
stop_result = await query.async_stop()
assert stop_result == 'Success'
```
----------------------------------------
TITLE: Initializing Index Client with Explicit Credentials
DESCRIPTION: Python code to initialize the Upstash Vector Index client using explicit URL and token credentials that can be obtained from the Upstash console after creating a vector database.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/gettingstarted.mdx#_snippet_1
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(url="UPSTASH_VECTOR_REST_URL", token="UPSTASH_VECTOR_REST_TOKEN")
```
----------------------------------------
TITLE: Querying the Vector Index
DESCRIPTION: Example of how to query the document using the initialized query engine
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/llamaindex.mdx#_snippet_3
LANGUAGE: python
CODE:
```
# Initialize the query engine
query_engine = index.as_query_engine()
# Query the document about global warming
res1 = query_engine.query("What is global warming?")
print(res1)
res2 = query_engine.query("How should we modify our diets to reduce our carbon footprint?")
print(res2)
```
----------------------------------------
TITLE: Retrieving Namespace Information in PHP using Upstash Vector SDK
DESCRIPTION: This snippet demonstrates how to fetch information about specific namespaces using the getNamespaceInfo() method. It shows how to get info for both the default namespace and a custom namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/info.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
// Fetch the information of the default namespace.
$defaultNamespaceInfo = $index->getNamespaceInfo();
// Fetch the information on a specific namespace.
$myNamespaceInfo = $index->namespace('my-namespace')->getNamespaceInfo();
```
----------------------------------------
TITLE: Querying Text Data with Upstash Vector
DESCRIPTION: Examples of querying raw text data from Upstash Vector database using various programming languages. The code shows how to perform similarity searches with specified parameters like top_k and metadata inclusion.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/embeddingmodels.mdx#_snippet_1
LANGUAGE: Python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.query(
data="What is Upstash?",
top_k=1,
include_metadata=True,
)
```
LANGUAGE: JavaScript
CODE:
```
import { Index } from "@upstash/vector"
const index = new Index({
url: "UPSTASH_VECTOR_REST_URL",
token: "UPSTASH_VECTOR_REST_TOKEN",
})
await index.query({
data: "What is Upstash?",
topK: 1,
includeMetadata: true,
})
```
LANGUAGE: Go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN")
index.QueryData(vector.QueryData{
Data: "What is Upstash?",
TopK: 1,
IncludeMetadata: true,
})
}
```
LANGUAGE: PHP
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataQuery;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->queryData(new DataQuery(
data: 'What is Upstash?',
topK: 1,
includeMetadata: true,
));
```
LANGUAGE: Shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query-data \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"data": "What is Upstash?", "topK": 1, "includeMetadata": "true"}'
```
----------------------------------------
TITLE: Upserting to a Hybrid Index in PHP
DESCRIPTION: This snippet demonstrates how to upsert to a hybrid index in Upstash Vector, which requires both dense and sparse vector data. It combines a standard vector with a SparseVector object to provide both vector types as required by hybrid indexes.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_8
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use Upstash\Vector\SparseVector;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsert(new VectorUpsert(
id: '1',
vector: createRandomVector(dimensions: 1536),
sparseVector: new SparseVector(
indices: [0, 1],
values: [1.0, 2.0],
),
));
```
----------------------------------------
TITLE: Setting Custom Max Idle Time using REST API with curl
DESCRIPTION: Demonstrates how to configure the maximum idle time for a resumable query using direct REST API calls with curl. This determines how long a query can remain inactive before being automatically terminated.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/resumablequery.mdx#_snippet_15
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"vector": [0.1, 0.2],
"topK": 2,
"includeMetadata": true,
"maxIdle": 7200
}'
```
----------------------------------------
TITLE: Fetching Vectors with Pagination using cURL
DESCRIPTION: HTTP request to range over vectors from the default namespace, starting with cursor 0, limiting to 2 results per page, and including metadata in the response.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/range.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/range \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "cursor": "0", "limit": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Complete Example of Vector Upsert Operation
DESCRIPTION: A comprehensive Python example that demonstrates how to initialize the client, generate a random vector, attach metadata, and upsert it into the Upstash Vector database. This showcases the basic workflow of the SDK.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/gettingstarted.mdx#_snippet_3
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index
# Initialize the index client using environment variables
index = Index.from_env()
def main():
# Define the dimension based on the index configuration
dimension = 128
# Generate a random vector for upsert
vector_to_upsert = [random.random() for _ in range(dimension)]
# Additional metadata associated with the vector
metadata = {"text": "example test for metadata"}
# Upsert the vector into the index
index.upsert(vectors=[
("id-for-vector", vector_to_upsert, metadata)
])
```
----------------------------------------
TITLE: Upserting Sparse Vectors in PHP
DESCRIPTION: Example of upserting sparse vectors to an Upstash Vector index in PHP using the Upstash Vector library. It shows how to create and upsert multiple sparse vectors with their dimension indices and values.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_4
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use Upstash\Vector\SparseVector;
$index = new Index(
url: 'UPSTASH_VECTOR_REST_URL',
token: 'UPSTASH_VECTOR_REST_TOKEN',
);
$index->upsertMany([
new VectorUpsert(
id: 'id-0',
sparseVector: new SparseVector(
indices: [1, 2],
values: [0.1, 0.2],
),
),
new VectorUpsert(
id: 'id-1',
sparseVector: new SparseVector(
indices: [123, 44232],
values: [0.5, 0.4],
),
),
]);
```
----------------------------------------
TITLE: Retrieving Vector Index Information with cURL
DESCRIPTION: Example of how to query the Upstash Vector Index Info API using cURL. This request requires an Upstash Vector REST URL and a bearer token for authentication.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/info.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/info \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN"
```
----------------------------------------
TITLE: Execute Resumable Vector Query with cURL
DESCRIPTION: Example of making a POST request to resume a vector similarity search using cURL. Requires authentication via bearer token and accepts a query UUID and number of additional results to fetch.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/resumable-query/resume.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query-next \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"uuid": "550e8400-e29b-41d4-a716-446655440000",
"additionalK": 2
}'
```
----------------------------------------
TITLE: Implementing Command-Level TypeScript Types
DESCRIPTION: Using TypeScript types at the individual command level for specific vector operations.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/getting-started.mdx#_snippet_5
LANGUAGE: typescript
CODE:
```
import { Index } from "@upstash/vector";
type Metadata = { genre: string, year: number };
const index = new Index();
index.upsert<Metadata>({ id: 1, vector: [...], metadata: {
genre: "comedy",
year: 1990
}});
```
----------------------------------------
TITLE: Retrieving Index Statistics with Upstash Vector Info Method in Python
DESCRIPTION: This snippet demonstrates how to use the info method in Upstash Vector to get statistical information about a vector index. It initializes an index from environment variables, calls the info method, and then displays various properties including vector counts, index size, dimensions, similarity function, and namespace statistics.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/info.mdx#_snippet_0
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
from upstash_vector import Index
index = Index.from_env()
# Get statistical information about the index
info_result = index.info()
# Display the info result
print("Vector Count:", info_result.vector_count)
print("Pending Vector Count:", info_result.pending_vector_count)
print("Index Size:", info_result.index_size)
print("Dimension:", info_result.dimension)
print("Similarity Function:", info_result.similarity_function)
for ns, ns_info in info_result.namespaces.items():
print("Namespace:", ns, "Vector Count:", ns_info.vector_count)
print("Namespace:", ns, "Pending Vector Count:", ns_info.pending_vector_count)
```
----------------------------------------
TITLE: Upserting a Vector using cURL and Upstash Vector REST API
DESCRIPTION: This command uses cURL to upsert a vector with ID 'id-0' into an Upstash Vector database. It requires the UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN environment variables to be set for authentication.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/get-started.mdx#_snippet_0
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{"id": "id-0", "vector": [0.87, 0.99]}'
```
----------------------------------------
TITLE: Fetching a Vector with Namespace Specification in Python
DESCRIPTION: This example demonstrates how to fetch a vector while specifying a namespace to operate on. When a namespace is provided, the fetch operation retrieves vectors from that specific namespace rather than the default one.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/fetch.mdx#_snippet_2
LANGUAGE: python
CODE:
```
index.fetch("id-4", namespace="ns")
```
----------------------------------------
TITLE: Successful query response format
DESCRIPTION: Example of a successful response from the query endpoint showing an array of matched vectors with their IDs, similarity scores, and optional metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query-data.mdx#_snippet_3
LANGUAGE: json
CODE:
```
{
"result": [
{
"id": "id-0",
"score": 1.0,
"metadata": {
"link": "upstash.com"
}
},
{
"id": "id-1",
"score": 0.99996454
}
]
}
```
----------------------------------------
TITLE: Initializing Client with Environment Variables
DESCRIPTION: Example of initializing the Upstash Vector client using environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/overview-backup.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
import { Index } from "@upstash/vector";
const index = new Index();
```
----------------------------------------
TITLE: Creating an Async Resumable Query in Python
DESCRIPTION: Create a resumable query using the AsyncIndex class for asynchronous vector similarity search operations.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_4
LANGUAGE: python
CODE:
```
query = await async_index.resumable_query(
vector=[0.1, 0.2],
top_k=2,
include_metadata=True,
include_vectors=True,
namespace='your_namespace'
)
```
----------------------------------------
TITLE: Metadata Filter Examples using SQL-like Syntax
DESCRIPTION: Various examples of filter expressions using SQL-like syntax supported by Upstash Vector for filtering based on different metadata conditions.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_6
LANGUAGE: sql
CODE:
```
country = 'Turkey' AND population = 15460000 AND is_capital = false
```
LANGUAGE: sql
CODE:
```
country != 'Germany' AND population != 12500000 AND is_capital != true
```
LANGUAGE: sql
CODE:
```
population < 20000000 OR geography.coordinates.longitude < 30.0
```
LANGUAGE: sql
CODE:
```
population <= 20000000 OR geography.coordinates.longitude <= 30.0
```
LANGUAGE: sql
CODE:
```
population > 10000000 OR geography.coordinates.latitude > 39.5
```
LANGUAGE: sql
CODE:
```
population >= 10000000 OR geography.coordinates.latitude >= 39.5
```
LANGUAGE: sql
CODE:
```
city GLOB '?[sz]*[^m-z]'
```
LANGUAGE: sql
CODE:
```
city NOT GLOB 'A*'
```
LANGUAGE: sql
CODE:
```
country IN ('Germany', 'Turkey', 'France')
```
LANGUAGE: sql
CODE:
```
economy.currency NOT IN ('USD', 'EUR')
```
LANGUAGE: sql
CODE:
```
economy.major_industries CONTAINS 'Tourism'
```
LANGUAGE: sql
CODE:
```
economy.major_industries NOT CONTAINS 'Steel Production'
```
LANGUAGE: sql
CODE:
```
HAS FIELD geography.coordinates
```
LANGUAGE: sql
CODE:
```
HAS NOT FIELD geography.coordinates.longitude
```
LANGUAGE: sql
CODE:
```
country = 'Turkey' AND population > 10000000
```
LANGUAGE: sql
CODE:
```
country = 'Turkey' AND (population > 10000000 OR is_capital = false)
```
LANGUAGE: sql
CODE:
```
economy.currency != 'USD' AND geography.coordinates.latitude >= 35.0
```
LANGUAGE: sql
CODE:
```
economy.major_industries[0] = 'Tourism'
```
LANGUAGE: sql
CODE:
```
economy.major_industries[#-1] = 'Finance'
```
----------------------------------------
TITLE: Accessing Namespace Information Properties in PHP
DESCRIPTION: This snippet shows how to access properties of the NamespaceInfo object returned by getNamespaceInfo(). It includes the number of vectors ready to query and the number of pending vectors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/info.mdx#_snippet_3
LANGUAGE: php
CODE:
```
// To know the number of vectors ready to query.
$myNamespaceInfo->vectorCount;
// To know the number of vectors that are getting indexed.
$myNamespaceInfo->pendingVectorCount;
```
----------------------------------------
TITLE: Error Handling for Resumable Queries in Python
DESCRIPTION: Handle errors that can occur when trying to fetch results from a stopped query or stopping an already stopped query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_8
LANGUAGE: python
CODE:
```
with pytest.raises(ClientError):
query.fetch_next(1)
query.async_fetch_next(1)
for async with pytest.raises(ClientError):
query.stop() # or await query.async_stop() for async
```
----------------------------------------
TITLE: Using Vector Facade in Laravel
DESCRIPTION: Example of accessing Upstash Vector using the Laravel facade pattern to fetch index information.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/laravel.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Laravel\Facades\Vector;
Vector::getInfo(); // Fetches the index info.
```
----------------------------------------
TITLE: Upserting Vectors Using Vector Object in Python
DESCRIPTION: This snippet demonstrates how to upsert vectors into an Upstash Vector index using Vector objects. It initializes an index from environment variables, creates multiple Vector objects with random vector values, metadata, and unstructured data, then upserts them into the index.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/upsert.mdx#_snippet_0
LANGUAGE: python
CODE:
```
import random
from upstash_vector import Index, Vector
index = Index.from_env()
dimension = 128 # Adjust based on your index's dimension
upsert_amount = 100
vectors = [
Vector(
id=f"generated-id-{i}",
vector=[random.random() for _ in range(dimension)],
metadata={"some_field": f"some_value-{i}"},
data=f"some-unstructured-data-{i}",
)
for i in range(upsert_amount)
]
index.upsert(vectors=vectors)
```
----------------------------------------
TITLE: Retrieving Range of Vectors with Metadata in Python
DESCRIPTION: Code snippet showing how to retrieve a range of vectors with metadata in Python. It demonstrates using the range method with cursor pagination and the include_metadata flag.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_16
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index(
url="UPSTASH_VECTOR_REST_URL",
token="UPSTASH_VECTOR_REST_TOKEN",
)
index.range(
cursor="0",
limit=3,
include_metadata=True,
)
```
----------------------------------------
TITLE: Multiple Data Upsert Operation in TypeScript
DESCRIPTION: Shows how to upsert multiple text data entries that will be converted to vector embeddings, with optional metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/upsert.mdx#_snippet_5
LANGUAGE: typescript
CODE:
```
await index.upsert([
{
id: "6789",
data: "'Harry Potter' follows the journey of a young wizard, Harry Potter, as he attends Hogwarts School of Witchcraft and Wizardry, forms deep friendships, and confronts the dark wizard Voldemort, who seeks immortality and domination over the magical world.",
},
{
id: "1234",
data: "'The Lord of the Rings' follows Frodo Baggins and his allies on a quest to destroy a powerful ring and save Middle-earth from the dark lord Sauron.",
metadata: {
title: "Lord of The Rings",
genre: "drama",
category: "classic",
},
},
]);
```
----------------------------------------
TITLE: Deleting a Namespace in Upstash Vector using cURL
DESCRIPTION: This example demonstrates how to delete a namespace named 'ns' from an Upstash Vector index using cURL. The request requires authentication via a bearer token stored in the UPSTASH_VECTOR_REST_TOKEN environment variable.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/delete-namespace.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/delete-namespace/ns \
-X DELETE \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN"
```
----------------------------------------
TITLE: Vector Fetch with Not Found Handling in TypeScript
DESCRIPTION: Shows how the fetch operation handles non-existent vectors, returning null for vectors that aren't found while still returning existing vectors.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/fetch.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
await index.fetch(["2", "3"]);
// [{ id: "2" }, null]
```
----------------------------------------
TITLE: Manual Initialization of Upstash Vector Client
DESCRIPTION: PHP code showing how to manually initialize the Upstash Vector client by directly passing URL and token parameters.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/getting-started.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
```
----------------------------------------
TITLE: Stopping a Resumable Query with cURL in Upstash Vector
DESCRIPTION: This example demonstrates how to use cURL to stop a resumable query by sending a POST request to the resumable-query-end endpoint. It requires the Upstash Vector REST URL and authentication token as environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/resumable-query/stop.mdx#_snippet_0
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/resumable-query-end \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"uuid": "550e8400-e29b-41d4-a716-446655440000"
}'
```
----------------------------------------
TITLE: Accessing Specific Upstash Vector Connection in Laravel
DESCRIPTION: Example of switching between different Vector connections in a Laravel application using the connection method.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/laravel.mdx#_snippet_7
LANGUAGE: php
CODE:
```
use Upstash\Vector\Laravel\Facades\Vector;
Vector::connection('another')->getInfo();
```
----------------------------------------
TITLE: Calculating Euclidean Distance Score in Vector Indexing
DESCRIPTION: Formula for calculating the Euclidean distance similarity score between two vectors. The score is normalized to a range of 0-1 by using the reciprocal of 1 plus the squared distance.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/similarityfunctions.mdx#_snippet_1
LANGUAGE: plaintext
CODE:
```
1 / (1 + squared_distance(v1, v2))
```
----------------------------------------
TITLE: Resetting All Namespaces in Upstash Vector Using Python
DESCRIPTION: This snippet demonstrates how to reset all namespaces in an Upstash Vector index at once. It initializes an Index instance and calls the reset method with the all parameter set to True to clear vectors and metadata from all namespaces.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/reset.mdx#_snippet_2
LANGUAGE: python
CODE:
```
from upstash_vector import Index
index = Index.from_env()
index.reset(all=True)
```
----------------------------------------
TITLE: Creating Chat UI with Vercel AI SDK in TypeScript React
DESCRIPTION: This code snippet implements the chat UI using the Vercel AI SDK's useChat hook. It renders messages, handles input changes, and submits user messages to the chat API.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_6
LANGUAGE: typescript
CODE:
```
'use client'
import { useChat } from 'ai/react'
export default function Home() {
// This hook handles message state + streaming from /api/chat
const { messages, input, handleInputChange, handleSubmit } = useChat({
// You can enable multi-step calls if you want the model to call multiple tools in one session
maxSteps: 3,
})
return (
<div className="mx-auto max-w-md py-6">
<h1 className="text-xl font-bold mb-4">RAG Chatbot with Upstash Vector</h1>
{/* Render messages */}
<div className="space-y-2 mb-8">
{messages.map(m => (
<div key={m.id} className="border p-2 rounded">
<strong>{m.role}:</strong>
<div>
{/* If the model calls a tool, show which tool it called */}
{m.content.length > 0 ? (
m.content
) : (
<i>calling tool: {m?.toolInvocations?.[0]?.toolName}</i>
)}
</div>
</div>
))}
</div>
{/* Text input */}
<form onSubmit={handleSubmit} className="flex gap-2">
<input
className="flex-1 border rounded px-2 py-1"
placeholder="Say something..."
value={input}
onChange={handleInputChange}
/>
<button className="px-4 py-1 bg-black text-white rounded" type="submit">
Send
</button>
</form>
</div>
)
}
```
----------------------------------------
TITLE: Batch Upserting Multiple Vectors in PHP
DESCRIPTION: This snippet demonstrates how to upsert multiple vectors at once into an Upstash Vector index using the upsertMany() method. It creates an array of VectorUpsert objects, each with a unique ID and vector data, improving performance by batching operations together.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use function Upstash\Vector\createRandomVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->upsertMany([
new VectorUpsert(
id: '1',
vector: createRandomVector(dimensions: 1536)
),
new VectorUpsert(
id: '2',
vector: createRandomVector(dimensions: 1536)
),
]);
```
----------------------------------------
TITLE: Fetching a Single Vector by ID in Python
DESCRIPTION: A simplified example showing how to fetch a single vector by providing just the vector ID. This is a more concise alternative to the list-based approach when only one vector is needed.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/fetch.mdx#_snippet_1
LANGUAGE: python
CODE:
```
index.fetch("id-4")
```
----------------------------------------
TITLE: Batch Upserting with Namespace in PHP
DESCRIPTION: Shows how to perform batch upserting operations within a specific namespace. Combines the benefits of batch processing with namespace organization.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-data.mdx#_snippet_3
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\DataUpsert;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->upsertDataMany([
new DataUpsert(id: '1', data: 'The capital of Japan is Tokyo'),
new DataUpsert(id: '2', data: 'The capital of France is Paris'),
new DataUpsert(id: '3', data: 'The capital of Germany is Berlin'),
]);
```
----------------------------------------
TITLE: Resetting All Namespaces with curl in Upstash Vector
DESCRIPTION: This example demonstrates how to reset all namespaces in an Upstash Vector index by using the 'all' query parameter with a curl DELETE request. It requires the Upstash Vector REST URL and authentication token as environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/reset.mdx#_snippet_2
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/reset?all \
-X DELETE \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN"
```
----------------------------------------
TITLE: Resetting Specific Namespace with curl in Upstash Vector
DESCRIPTION: This example shows how to reset a specific namespace named 'ns' in an Upstash Vector index using a curl DELETE request. It requires the Upstash Vector REST URL and authentication token as environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/reset.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/reset/ns \
-X DELETE \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN"
```
----------------------------------------
TITLE: Initializing Vector Client with Environment Variables
DESCRIPTION: Creating a new Vector Index instance using environment variables for authentication.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/getting-started.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
import { Index } from "@upstash/vector";
const index = new Index();
```
----------------------------------------
TITLE: Namespace-Specific Vector Query using cURL
DESCRIPTION: Example of querying vectors in a specific namespace using cURL, showing how to target a particular namespace for vector queries.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "vector": [0.1, 0.2], "topK": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Updating Vector Value in a Namespace using cURL
DESCRIPTION: This example shows how to update the vector value of a vector with ID 'id-2' in the 'ns' namespace. It sets the vector to a 2-dimensional array [0.1, 0.2] using the Upstash Vector REST API.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/update.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/update/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "id": "id-2", "vector": [0.1, 0.2] }'
```
----------------------------------------
TITLE: Resetting All Namespaces in TypeScript
DESCRIPTION: Shows how to reset all namespaces of a vector index by passing the all:true argument. This will clear all vectors and metadata across all namespaces. Returns 'Successful' on successful reset.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/reset.mdx#_snippet_1
LANGUAGE: typescript
CODE:
```
const responseReset = await index.reset({ all: true });
// 'Successful'
```
----------------------------------------
TITLE: Injecting Upstash Vector Index Into Laravel Controllers
DESCRIPTION: Example of dependency injection pattern for accessing Upstash Vector in Laravel controllers by injecting the IndexInterface.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/laravel.mdx#_snippet_3
LANGUAGE: php
CODE:
```
namespace App\Http\Controllers;
use Upstash\Vector\Contracts\IndexInterface;
class Controller
{
public function index(IndexInterface $index)
{
$namespaces = $index->listNamespaces();
return response()->json(['namespaces' => $namespaces]);
}
}
```
----------------------------------------
TITLE: Upserting Vectors with Metadata using curl
DESCRIPTION: Code snippet demonstrating how to upsert a vector with metadata using curl. It sends a POST request to the Upstash Vector REST API with a JSON payload containing the vector and URL metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/metadata.mdx#_snippet_4
LANGUAGE: shell
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{
"id":"id-0",
"vector":[0.9215,0.3897],
"metadata":{
"url":"https://imgur.com/z9AVZLb"
}
}'
```
----------------------------------------
TITLE: Environment Configuration Setup
DESCRIPTION: Environment variables configuration for Upstash Vector credentials including REST URL and token.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/gradio-application.mdx#_snippet_1
LANGUAGE: env
CODE:
```
UPSTASH_VECTOR_REST_URL=your_upstash_url
UPSTASH_VECTOR_REST_TOKEN=your_upstash_token
```
----------------------------------------
TITLE: Upserting to a Sparse Index with Namespace in PHP
DESCRIPTION: This snippet shows how to upsert vector data into a sparse index within a specific namespace in Upstash Vector. It combines the namespace() method with a SparseVector object to target the specified namespace with sparse vector data.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/commands/upsert-vectors.mdx#_snippet_7
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
use Upstash\Vector\VectorUpsert;
use Upstash\Vector\SparseVector;
$index = new Index(
url: "<UPSTASH_VECTOR_REST_URL>",
token: "<UPSTASH_VECTOR_REST_TOKEN>",
);
$index->namespace('my-namespace')->upsert(new VectorUpsert(
id: '1',
sparseVector: new SparseVector(
indices: [0, 1],
values: [1.0, 2.0],
),
));
```
----------------------------------------
TITLE: Environment Variables Configuration
DESCRIPTION: Configuration settings for Upstash Vector credentials in the .env file.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/langchain.mdx#_snippet_0
LANGUAGE: plaintext
CODE:
```
UPSTASH_VECTOR_REST_URL=your_upstash_url
UPSTASH_VECTOR_REST_TOKEN=your_upstash_token
```
----------------------------------------
TITLE: Upserting Single Vector to a Specific Namespace with cURL
DESCRIPTION: This example shows how to upsert a single vector to a specific namespace ('ns') using cURL. The request includes a vector ID, dense vector values, and metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/upsert.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/upsert/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "id": "id-2", "vector": [0.1, 0.2], "metadata": { "link": "upstash.com" } }'
```
----------------------------------------
TITLE: Deleting Vectors by ID Prefix in Typescript
DESCRIPTION: Demonstrates how to delete all vectors with IDs starting with a specific prefix. This is useful for batch operations where vectors share a common ID pattern.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/commands/delete.mdx#_snippet_2
LANGUAGE: typescript
CODE:
```
const response = await index.delete({
prefix: "article_",
});
// { deleted: 3 }
```
----------------------------------------
TITLE: Installing Required Dependencies with Package Managers
DESCRIPTION: Commands to install necessary packages including AI SDK, OpenAI, Zod, and Upstash Vector using different package managers.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/ai-sdk.mdx#_snippet_0
LANGUAGE: bash
CODE:
```
npm install @ai-sdk/openai ai zod @upstash/vector
```
----------------------------------------
TITLE: Initializing Upstash Vector Client from Environment Variables
DESCRIPTION: PHP code snippet demonstrating how to initialize the Upstash Vector client using environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/getting-started.mdx#_snippet_2
LANGUAGE: php
CODE:
```
use Upstash\Vector\Index;
$index = Index::fromEnv();
```
----------------------------------------
TITLE: Specifying Namespace for Vector Updates in Upstash Vector
DESCRIPTION: A code snippet showing how to specify a namespace when updating vectors in Upstash Vector. When no namespace is provided, the update operation will use the default namespace.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/update.mdx#_snippet_2
LANGUAGE: python
CODE:
```
index.update(..., namespace="ns")
```
----------------------------------------
TITLE: Installing Upstash Vector SDK
DESCRIPTION: Commands to install the @upstash/vector package using npm or pnpm package managers.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/getting-started.mdx#_snippet_0
LANGUAGE: shell
CODE:
```
npm install @upstash/vector
```
LANGUAGE: shell
CODE:
```
pnpm add @upstash/vector
```
----------------------------------------
TITLE: Deleting Vectors by ID in Custom Namespace Using cURL in Upstash Vector API
DESCRIPTION: Demonstrates how to delete vectors by their IDs within a specific namespace using a cURL request. The namespace 'ns' is specified in the URL path, and authentication is provided via bearer token.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/delete.mdx#_snippet_1
LANGUAGE: sh
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/delete/ns \
-X DELETE \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "ids": [ "id-0", "id-1" ] }'
```
----------------------------------------
TITLE: Installing Required Packages for LangChain and Upstash Vector
DESCRIPTION: Commands to install the necessary Python packages including upstash-vector, langchain, langchain-community, and python-dotenv using pip package manager.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/langchain.mdx#_snippet_0
LANGUAGE: bash
CODE:
```
pip install upstash-vector langchain langchain-community python-dotenv
```
----------------------------------------
TITLE: Querying vector data in specific namespace
DESCRIPTION: Curl request that targets a specific namespace 'ns' when performing vector similarity search, which allows for data organization and isolation within the vector database.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/query-data.mdx#_snippet_1
LANGUAGE: curl
CODE:
```
curl $UPSTASH_VECTOR_REST_URL/query-data/ns \
-X POST \
-H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \
-d '{ "data": "What is Upstash?", "topK": 2, "includeMetadata": true }'
```
----------------------------------------
TITLE: Installing Required Python Packages
DESCRIPTION: Command to install necessary Python packages including llama-index, upstash-vector, and related dependencies.
SOURCE: https://github.com/upstash/docs/blob/main/vector/integrations/llamaindex.mdx#_snippet_0
LANGUAGE: bash
CODE:
```
pip install llama-index upstash-vector llama-index-vector-stores-upstash python-dotenv
```
----------------------------------------
TITLE: Representing Dense vs Sparse Vectors in Python
DESCRIPTION: Example showing the difference between dense vector representation (with thousands of dimensions) and sparse vector representation (with significantly fewer non-zero dimensions).
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/sparseindexes.mdx#_snippet_0
LANGUAGE: python
CODE:
```
dense = [0.1, 0.3, , ...thousands of non-zero values..., 0.5, 0.2]
sparse = (
[23, 42, 5523, 123987, 240001], # some low number of dimension indices
[0.1, 0.3, 0.1, 0.2, 0.5], # non-zero values corresponding to dimensions
)
```
----------------------------------------
TITLE: Error Response for Non-existent Namespace in Upstash Vector
DESCRIPTION: The JSON error response structure when attempting to delete a namespace that doesn't exist. Returns a 404 Not Found status with an explanatory error message.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/delete-namespace.mdx#_snippet_2
LANGUAGE: json
CODE:
```
{
"error": "Namespace ns for the index $NAME does not exist",
"status": 404
}
```
----------------------------------------
TITLE: Range Vectors Response Format
DESCRIPTION: Example JSON response from the Range Vectors endpoint showing the nextCursor for pagination and an array of vectors with their IDs and optional metadata.
SOURCE: https://github.com/upstash/docs/blob/main/vector/api/endpoints/range.mdx#_snippet_2
LANGUAGE: json
CODE:
```
{
"result": {
"nextCursor": "2",
"vectors": [
{
"id": "id-0",
"metadata": {
"link": "upstash.com"
}
},
{
"id": "id-1"
}
]
}
}
```
----------------------------------------
TITLE: Installing Required Dependencies
DESCRIPTION: Command to install necessary Python packages including LangChain, sentence-transformers, and Upstash Vector client.
SOURCE: https://github.com/upstash/docs/blob/main/vector/tutorials/huggingface-embeddings.mdx#_snippet_0
LANGUAGE: bash
CODE:
```
pip install langchain sentence_transformers upstash-vector python-dotenv langchain-community langchain-huggingface
```
----------------------------------------
TITLE: Custom Reranking with Separate Dense and Sparse Queries in Go
DESCRIPTION: Demonstrates how to perform separate queries for dense and sparse components in Go, allowing for custom reranking. This approach is useful when standard fusion algorithms don't meet specific requirements.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/hybridindexes.mdx#_snippet_4
LANGUAGE: Go
CODE:
```
package main
import (
"github.com/upstash/vector-go"
)
func main() {
index := vector.NewIndex(
"UPSTASH_VECTOR_REST_URL",
"UPSTASH_VECTOR_REST_TOKEN",
)
denseScores, err := index.Query(vector.Query{
Vector: []float32{0.5, 0.4},
})
sparseScores, err := index.Query(vector.Query{
SparseVector: &vector.SparseVector{
Indices: []int32{3, 5},
Values: []float32{0.3, 05},
},
})
// Rerank dense and sparse results as you like here
}
```
----------------------------------------
TITLE: Example Metadata Structure in JSON Format
DESCRIPTION: A sample metadata structure that demonstrates the different value types that can be filtered in Upstash Vector, including nested objects and arrays.
SOURCE: https://github.com/upstash/docs/blob/main/vector/features/filtering.mdx#_snippet_0
LANGUAGE: json
CODE:
```
{
"city": "Istanbul",
"country": "Turkey",
"is_capital": false,
"population": 15460000,
"geography": {
"continent": "Asia",
"coordinates": {
"latitude": 41.0082,
"longitude": 28.9784
}
},
"economy": {
"currency": "TRY",
"major_industries": [
"Tourism",
"Textiles",
"Finance"
]
}
}
```
----------------------------------------
TITLE: Basic Upstash Vector Configuration in Laravel
DESCRIPTION: Default configuration file for Upstash Vector with a single connection setup using environment variables.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/php/laravel.mdx#_snippet_5
LANGUAGE: php
CODE:
```
return [
'default' => env('UPSTASH_VECTOR_CONNECTION', 'default'),
'connections' => [
'default' => [
'url' => env('UPSTASH_VECTOR_REST_URL'),
'token' => env('UPSTASH_VECTOR_REST_TOKEN'),
],
],
];
```
----------------------------------------
TITLE: Fetching More Results Asynchronously in Python
DESCRIPTION: Fetch the next batch of results asynchronously in a resumable query.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/py/example_calls/resumable-query.mdx#_snippet_6
LANGUAGE: python
CODE:
```
next_results = await query.async_fetch_next(number_of_results)
```
----------------------------------------
TITLE: Defining Index-Level TypeScript Types
DESCRIPTION: Implementing strong type safety at the index level by defining metadata types for vector operations.
SOURCE: https://github.com/upstash/docs/blob/main/vector/sdks/ts/getting-started.mdx#_snippet_4
LANGUAGE: typescript
CODE:
```
import { Index } from "@upstash/vector";
type Metadata = { genre: string, year: number };
const index = new Index<Metadata>();
```