LlamaIndex

https://github.com/run-llama/llama_index
Admin
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Tokens:2,829,998
Snippets:18,836
Trust Score:8.7
License:MIT
Update:1 week ago
Show doc for...
Tokens:
Raw
### Set up and start local MCP server

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-mcp/examples/mcp.ipynb

Clone the repository, install required dependencies, configure environment variables, and launch the SSE MCP server.

```bash
# get the code
git clone https://github.com/run-llama/llama_index
cd llama_index/llama-index-integrations/tools/llama-index-tools-mcp/examples

# install dependencies
pip install ipinfo

cp .env.example .env
# NOTE: edit the .env file to have the correct values!

# run the server
python mcp_server.py --server_type=sse
```

--------------------------------

### Start Xinference server output example

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/xinference_local_deployment.ipynb

Example terminal output when running `xinference`, displaying the local endpoint URL and worker startup logs.

```shell
INFO:xinference:Xinference successfully started. Endpoint: http://127.0.0.1:9997
INFO:xinference.core.service:Worker 127.0.0.1:21561 has been added successfully
INFO:xinference.deploy.worker:Xinference worker successfully started.
```

--------------------------------

### Install dependencies

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-rayyan/examples/rayyan-loader.ipynb

Install the required packages from notebook-requirements.txt.

```bash
pip install -r notebook-requirements.txt
```

--------------------------------

### Install requirements

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-earnings-call-transcript/README.md

Install the required dependencies from requirements.txt.

```text
pip install -r requirements.txt
```

--------------------------------

### Install VideoDB and LlamaIndex packages

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/retrievers/llama-index-retrievers-videodb/README.md

Install the required packages using pip to get started with VideoDB Retriever in LlamaIndex.

```shell
pip install llama-index llama-index-retrievers-videodb videodb

```

--------------------------------

### Build and serve documentation locally

Source: https://github.com/run-llama/llama_index/blob/main/docs/DOCS_README.md

Starts the local server to build and browse the documentation.

```shell
poetry run serve
```

--------------------------------

### Install torch_geometric

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-docstring-walker/examples/docstringwalker_example.ipynb

Installs torch_geometric for multi-module docstring inspection examples.

```python
!pip install torch_geometric
```

--------------------------------

### Install Prerequisites and Download Sample Data

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/data_connectors/PathwayReaderDemo.ipynb

Installs the required pathway and llama-index packages, then downloads sample README data into a local directory.

```python
%pip install pathway
%pip install llama-index-embeddings-openai
```

```python
!mkdir -p 'data/'
!wget 'https://gist.githubusercontent.com/janchorowski/dd22a293f3d99d1b726eedc7d46d2fc0/raw/pathway_readme.md' -O 'data/pathway_readme.md'
```

--------------------------------

### Install llama-index-readers-mangoapps-guides package

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-mangoapps-guides/README.md

Install the Mangoapps Guides reader integration package using pip.

```bash
pip install llama-index-readers-mangoapps-guides

```

--------------------------------

### Install Triton CLI

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/nvidia_triton.ipynb

Installs the Triton Command Line Interface from GitHub to manage and start models.

```shell
pip install git+https://github.com/triton-inference-server/triton_cli.git
```

--------------------------------

### Run basic.py Example

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/llms/llama-index-llms-gaudi/examples/README.md

Executes the basic text completion example using GaudiLLM on Intel Gaudi.

```bash
python basic.py
```

--------------------------------

### Install required packages

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/output_parsing/guidance_sub_question.ipynb

Install LlamaIndex and the Guidance question generation extension in environment setups such as Google Colab.

```python
%pip install llama-index-question-gen-guidance
```

```python
!pip install llama-index
```

--------------------------------

### Run example script with uv

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/embeddings/llama-index-embeddings-heroku/README.md

Execute a sample script from the examples directory using uv.

```bash
cd examples
uv run python basic_usage.py
```

--------------------------------

### Basic Starter Query Example

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/getting_started/faq.mdx

Loads documents from a directory, creates a VectorStoreIndex, and runs a basic query using a query engine.

```python
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)
```

--------------------------------

### Install Wikipedia Tool Spec via pip

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-core/llama_index/core/tools/tool_spec/load_and_search/README.md

Installs the llama-index-tools-wikipedia package required for the Wikipedia tool example.

```bash
pip install llama-index-tools-wikipedia

```

--------------------------------

### Initialize Chroma Client and Collection

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/chroma_metadata_filter.ipynb

Creates an in-memory ephemeral Chroma client and initializes a collection named 'quickstart'.

```python
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")
```

--------------------------------

### Install RAG Example Dependencies

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-objectbox/README.md

Install the required core LlamaIndex package, HuggingFace embeddings, and Gemini LLM integrations.

```commandline
pip install llama-index --quiet
pip install llama-index-embeddings-huggingface --quiet
pip install llama-index-llms-gemini --quiet
```

--------------------------------

### Custom Package Installation with Ollama and HuggingFace

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/getting_started/installation.mdx

Installs a selective set of packages for local model setups without OpenAI dependencies.

```bash
pip install llama-index-core llama-index-readers-file llama-index-llms-ollama llama-index-embeddings-huggingface
```

--------------------------------

### Create Directories and Download Sample PDF

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/multi_modal/multimodal_rag_guardrail_gemini_llmguard_llmguard.ipynb

Creates local data and image directories, then downloads the sample investor meeting PDF deck using wget.

```python
!mkdir data
!mkdir data_images
!wget "https://static.conocophillips.com/files/2023-conocophillips-aim-presentation.pdf" -O data/conocophillips.pdf
```

```text
Output:
mkdir: data: File exists
mkdir: data_images: File exists
zsh:1: command not found: wget
```

--------------------------------

### Set up JaguarDB and Python packages on Linux

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/JaguarIndexDemo.ipynb

Installs JaguarDB using the setup shell script and installs the required Python packages.

```bash
curl -fsSL http://jaguardb.com/install.sh | sh\n
pip install -U llama-index
pip install -U jaguardb-http-client
```

--------------------------------

### Verify starter project directory structure

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/getting_started/starter_example_local.mdx

Shows the expected directory layout after downloading sample data.

```text
├── starter.py └── data    └── paul_graham_essay.txt
```

--------------------------------

### Install optional dependencies for Bedrock Converse

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-aws-bedrock-agentcore/README.md

Installs the base LlamaIndex package and Bedrock Converse LLM integration required to run the examples.

```bash
pip install llama-index llama-index-llms-bedrock-converse
```

--------------------------------

### Serve docs for a minimal build

Source: https://github.com/run-llama/llama_index/blob/main/docs/DOCS_README.md

Skips both notebooks and API reference generation for the fastest build time.

```shell
poetry run serve --skip-notebooks --skip-reference
```

--------------------------------

### Download sample files

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/memory/custom_memory.ipynb

Download dummy image and python files used for demonstrating workflow context management.

```python
!wget https://mediaproxy.tvtropes.org/width/1200/https://static.tvtropes.org/pmwiki/pub/images/shrek_cover.png -O ./image.png
!wget https://raw.githubusercontent.com/run-llama/llama_index/refs/heads/main/llama-index-core/llama_index/core/memory/memory.py -O ./memory.py
```

--------------------------------

### Install and configure PostgreSQL with pgvector in Colab

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/postgres.ipynb

Installs PostgreSQL and postgresql-15-pgvector via apt, starts the PostgreSQL service, configures the default user password, and creates the target database.

```python
!sudo apt update
!echo | sudo apt install -y postgresql-common
!echo | sudo /usr/share/postgresql-common/pgdg/apt.postgresql.org.sh
!echo | sudo apt install postgresql-15-pgvector
!sudo service postgresql start
!sudo -u postgres psql -c "ALTER USER postgres PASSWORD 'password';"
!sudo -u postgres psql -c "CREATE DATABASE vector_db;"
```

--------------------------------

### Create and activate virtual environment with uv

Source: https://github.com/run-llama/llama_index/blob/main/llama-dev/README.md

Initial setup step to create and activate a Python virtual environment.

```bash
uv venv
source .venv/bin/activate
```

--------------------------------

### Install the Package

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-azurepostgresql/README.md

Install the package and its dependencies using uv, pip, or poetry.

```bash
uv pip install .
# or
pip install .
# or
poetry install
```

--------------------------------

### Start Neo4j Database Server for Graph RAG

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/embeddings/llama-index-embeddings-gaudi/examples/README.md

Run a Neo4j Docker container configured with the APOC plugin and authentication required for Graph RAG examples.

```shell
docker run --restart always --publish=7474:7474 --publish=7687:7687 --env NEO4J_AUTH=neo4j/<neo4j-server-password> -v $PWD/data:/data -v $PWD/plugins:/plugins --name neo4j-apoc -e NEO4J_apoc_export_file_enabled=true -e NEO4J_apoc_import_file_enabled=true -e NEO4J_apoc_import_file_use__neo4j__config=true -e NEO4JLABS_PLUGINS=\[\"apoc\"\] -e NEO4J_dbms_security_procedures_unrestricted=apoc.\\\* neo4j:5.22.0
```

--------------------------------

### Copy sample environment files

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/understanding/putting_it_all_together/apps/fullstack_with_delphic.md

Sets up local configuration by creating necessary directories and copying sample environment files for the frontend, Django, and PostgreSQL.

```commandline
mkdir -p ./.envs/.local/
cp -a ./docs/sample_envs/local/.frontend ./frontend
cp -a ./docs/sample_envs/local/.django ./.envs/.local
cp -a ./docs/sample_envs/local/.postgres ./.envs/.local
```

--------------------------------

### Run GeminiLiveVoiceAgent with FunctionTool

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/voice_agents/llama-index-voice-agents-gemini-live/README.md

Runs a minimal GeminiLiveVoiceAgent example equipped with a custom weather function tool. Demonstrates starting the conversation and exporting filtered events and messages upon completion. Ensure GOOGLE_API_KEY is set in your environment or passed during agent initialization.

```python
from llama_index.voice_agents.gemini_live import GeminiLiveVoiceAgent
from llama_index.core.tools import FunctionTool
from llama_index.core.voice_agents import BaseVoiceAgentEvent
from llama_index.core.llms import ChatMessage, TextBlock
from typing import List
import random
import json


# use filter functions to export messages and events without your terminal being swamped by base64-encoded audio bytes :)
def filter_events(
    events: List[BaseVoiceAgentEvent],
) -> List[BaseVoiceAgentEvent]:
    evs = []
    for event in events:
        if not "audio" in event.type_t:
            evs.append(event)
    return evs


def filter_messages(messages: List[ChatMessage]) -> List[ChatMessage]:
    msgs = []
    for message in messages:
        msg = ChatMessage(role=message.role, blocks=[])
        for b in message.blocks:
            if isinstance(b, TextBlock):
                msg.blocks.append(b)
        if len(msg.blocks) > 0:
            msgs.append(msg)
    return msgs


def get_weather(location: str) -> dict:
    """Fetch weather data for a given location."""
    return json.dumps(
        {
            "location": location,
            "temperature_c": round(random.uniform(15, 30), 1),
            "humidity_percent": random.randint(40, 90),
            "wind_speed_kmh": round(random.uniform(5, 25), 1),
            "precipitation_probability_percent": random.randint(0, 100),
        },
        indent=4,
    )


weather_tool = FunctionTool.from_defaults(
    fn=get_weather,
    name="get_weather",
    description="Get the weather at a given location",
)


async def main():
    conversation = GeminiLiveVoiceAgent(tools=[weather_tool])

    await conversation.start()

    if conversation._quitflag:
        print("Events")
        print(conversation.export_events(filter=filter_events))
        print()
        print("Messages")
        print(conversation.export_messages(filter=filter_messages))


if __name__ == "__main__":
    import asyncio

    asyncio.run(main())
```

--------------------------------

### Install Qdrant client and FastEmbed dependencies

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/QdrantIndexDemo.ipynb

Install or upgrade the base client packages using pip.

```bash
!pip install -U qdrant_client fastembed
```

--------------------------------

### Install Superlinked Retriever Integration

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/retrievers/llama-index-retrievers-superlinked/examples/steam_games_example.ipynb

Installs or updates pip and installs the llama-index-retrievers-superlinked package.

```python
# Install dependencies for Colab\n
%pip -q install -U pip
%pip -q install llama-index-retrievers-superlinked
```

--------------------------------

### Install llama-index-readers-web using uv

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-web/llama_index/readers/web/oxylabs_web/README.md

Adds the llama-index-readers-web package using uv.

```shell
uv add llama-index-readers-web

```

--------------------------------

### Install and upgrade jaguardb-http-client with pip

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/JaguarIndexDemo.ipynb

Installs or upgrades the JaguarDB HTTP client library and displays the installation output.

```python
!pip install -U jaguardb-http-client
```

```text
Output:
Collecting jaguardb-http-client
  Using cached jaguardb_http_client-3.4.1-py2.py3-none-any.whl (15 kB)
Installing collected packages: jaguardb-http-client
Successfully installed jaguardb-http-client-3.4.1
```

--------------------------------

### Initialize QdrantVectorStore

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/community/integrations/vector_stores.md

Create a Qdrant client instance and connect it to QdrantVectorStore with a target collection.

```python
import qdrant_client
from llama_index.vector_stores.qdrant import QdrantVectorStore

# Creating a Qdrant vector store
client = qdrant_client.QdrantClient(
    host="<qdrant-host>", api_key="<qdrant-api-key>", https=True
)
collection_name = "paul_graham"

# construct vector store
vector_store = QdrantVectorStore(
    client=client,
    collection_name=collection_name,
)
```

--------------------------------

### Install uv on macOS and Linux

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/CONTRIBUTING.md

Installs the uv package manager on macOS and Linux using the official installation script.

```shell
curl -LsSf https://astral.sh/uv/install.sh | sh
```

--------------------------------

### Create an example Document

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/module_guides/loading/documents_and_nodes/usage_documents.md

Quickly generates a Document populated with default text for prototyping.

```python
document = Document.example()
```

--------------------------------

### Install required LlamaIndex dependencies

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/tools/eval_query_engine_tool.ipynb

Run pip install commands to install HuggingFace embeddings, OpenAI LLM, and OpenAI agent packages.

```python
%pip install llama-index-embeddings-huggingface
%pip install llama-index-llms-openai
%pip install llama-index-agents-openai
```

--------------------------------

### Set up Box Client with Developer Token

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-box/examples/box_ai_extract.ipynb

Initialize authentication and create a `BoxClient` instance using a developer token.

```python
# Setup Box Client
from box_sdk_gen import DeveloperTokenConfig, BoxDeveloperTokenAuth, BoxClient

BOX_DEV_TOKEN = "your_box_dev_token"

config = DeveloperTokenConfig(BOX_DEV_TOKEN)
auth = BoxDeveloperTokenAuth(config)
box_client = BoxClient(auth)
```

--------------------------------

### Instantiate AlibabaCloudOpenSearchStore

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/community/integrations/vector_stores.md

Configures and initializes AlibabaCloudOpenSearchStore using AlibabaCloudOpenSearchConfig.

```python
from llama_index.vector_stores.alibabacloud_opensearch import (
    AlibabaCloudOpenSearchStore,
    AlibabaCloudOpenSearchConfig,
)

config = AlibabaCloudOpenSearchConfig(
    endpoint="***",
    instance_id="***",
    username="your_username",
    password="your_password",
    table_name="llama",
)

vector_store = AlibabaCloudOpenSearchStore(config)
```

--------------------------------

### Install Core Dependencies and Tools

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/index_structs/knowledge_graph/knowledge_graph2.ipynb

Install additional packages including transformers, wikipedia, html2text, and pyvis, showing package installation output.

```python
!pip install llama_index transformers wikipedia html2text pyvis
```

```text
Output:
Requirement already satisfied: llama_index in /usr/local/lib/python3.10/dist-packages (0.8.37)
Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.33.3)
Requirement already satisfied: wikipedia in /usr/local/lib/python3.10/dist-packages (1.4.0)
Requirement already satisfied: html2text in /usr/local/lib/python3.10/dist-packages (2020.1.16)
Requirement already satisfied: pyvis in /usr/local/lib/python3.10/dist-packages (0.3.2)
Requirement already satisfied: tiktoken in /usr/local/lib/python3.10/dist-packages (from llama_index) (0.5.1)
Requirement already satisfied: dataclasses-json in /usr/local/lib/python3.10/dist-packages (from llama_index) (0.6.1)
Requirement already satisfied: langchain>=0.0.303 in /usr/local/lib/python3.10/dist-packages (from llama_index) (0.0.305)
Requirement already satisfied: sqlalchemy>=2.0.15 in /usr/local/lib/python3.10/dist-packages (from llama_index) (2.0.20)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from llama_index) (1.23.5)
Requirement already satisfied: tenacity<9.0.0,>=8.2.0 in /usr/local/lib/python3.10/dist-packages (from llama_index) (8.2.3)
Requirement already satisfied: openai>=0.26.4 in /usr/local/lib/python3.10/dist-packages (from llama_index) (0.28.1)
Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from llama_index) (1.5.3)
Requirement already satisfied: urllib3<2 in /usr/local/lib/python3.10/dist-packages (from llama_index) (1.26.16)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from llama_index) (2023.6.0)
Requirement already satisfied: typing-inspect>=0.8.0 in /usr/local/lib/python3.10/dist-packages (from llama_index) (0.9.0)
Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from llama_index) (4.5.0)
Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from llama_index) (4.11.2)
Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.10/dist-packages (from llama_index) (1.5.7)
Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from llama_index) (3.8.1)
Requirement already satisfied: tree-sitter-languages in /usr/local/lib/python3.10/dist-packages (from llama_index) (1.7.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.2)
Requirement already satisfied: huggingface-hub<1.0,>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.17.3)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)
Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)
Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)
Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.3.3)
Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)
Requirement already satisfied: ipython>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from pyvis) (7.34.0)
Requirement already satisfied: jinja2>=2.9.6 in /usr/local/lib/python3.10/dist-packages (from pyvis) (3.1.2)
Requirement already satisfied: jsonpickle>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from pyvis) (3.0.2)
Requirement already satisfied: networkx>=1.11 in /usr/local/lib/python3.10/dist-packages (from pyvis) (3.1)
Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.3.0->pyvis) (67.7.2)
Requirement already satisfied: jedi>=0.16 in /usr/local/lib/python3.10/dist-packages (from ipython>=5.3.0->pyvis) (0.19.0)
Requirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ipython>=5.3.0->pyvis) (4.4.2)
```

--------------------------------

### Install llama-index-readers-legacy-office

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/data_connectors/legacy_office_reader.ipynb

Install the legacy office reader package using pip. Note that Apache Tika requires Java to be installed on the system.

```python
%pip install llama-index-readers-legacy-office
```

--------------------------------

### Run Basic Usage Example

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/embeddings/llama-index-embeddings-gaudi/examples/README.md

Execute basic.py on Intel Gaudi with the necessary PyTorch HPU environment flags enabled.

```bash
PT_HPU_LAZY_ACC_PAR_MODE=1 PT_HPU_ENABLE_LAZY_COLLECTIVES=true python basic.py
```

--------------------------------

### Initialize VertexAIVectorStore and StorageContext

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/VertexAIVectorSearchDemo.ipynb

Set up a Vertex AI vector store using project configurations, endpoints, and a GCS bucket, then construct the storage context.

```python
# setup storage
vector_store = VertexAIVectorStore(
    project_id=PROJECT_ID,
    region=REGION,
    index_id=vs_index.resource_name,
    endpoint_id=vs_endpoint.resource_name,
    gcs_bucket_name=GCS_BUCKET_NAME,
)

# set storage context
storage_context = StorageContext.from_defaults(vector_store=vector_store)
```

--------------------------------

### Install llama-index-readers-database

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/data_connectors/DatabaseReaderDemo.ipynb

Installs the LlamaIndex DatabaseReader package.

```python
%pip install llama-index-readers-database
```

--------------------------------

### Set up global environment with uv sync

Source: https://github.com/run-llama/llama_index/blob/main/CONTRIBUTING.md

Run at the root of the repository to set up the global virtual environment used for pre-commit hooks and linters.

```bash
uv sync
```

--------------------------------

### Set up AlloyDBChatStore with SimpleChatEngine

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/module_guides/storing/chat_stores.md

Initialize an AlloyDB engine and chat store synchronously, then connect it to a Vertex LLM and SimpleChatEngine.

```python
from llama_index.core.chat_engine import SimpleChatEngine
from llama_index.core.memory import ChatMemoryBuffer
from llama_index_alloydb_pg import AlloyDBChatStore, AlloyDBEngine
from llama_index.llms.vertex import Vertex
import asyncio

# Replace with your own AlloyDB info
engine = AlloyDBEngine.from_instance(
    project_id=PROJECT_ID,
    region=REGION,
    cluster=CLUSTER,
    instance=INSTANCE,
    database=DATABASE,
    user=USER,
    password=PASSWORD,
)

engine.init_chat_store_table(table_name=TABLE_NAME)

chat_store = AlloyDBChatStore.create_sync(
    engine=engine,
    table_name=TABLE_NAME,
)

memory = ChatMemoryBuffer.from_defaults(
    token_limit=3000,
    chat_store=chat_store,
    chat_store_key="user1",
)

llm = Vertex(model="gemini-1.5-flash-002", project=PROJECT_ID)

chat_engine = SimpleChatEngine(memory=memory, llm=llm, prefix_messages=[])

response = chat_engine.chat("Hello.")

print(response)
```

--------------------------------

### Install Older LlamaIndex Version

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/ingestion/async_ingestion_pipeline.ipynb

Installs a version of llama_index older than 0.9.6 via pip. Restart the notebook kernel after installation to use the downgraded package.

```python
!pip install "llama_index<0.9.6"
```

```text
Output:
Collecting llama_index<0.9.6
  Obtaining dependency information for llama_index<0.9.6 from https://files.pythonhosted.org/packages/ac/3c/dee8ec4fecaaeabbd8a61ade9ddb6af09d05553c2a0acbebd1b559eaeb30/llama_index-0.9.5-py3-none-any.whl.metadata
  Downloading llama_index-0.9.5-py3-none-any.whl.metadata (8.2 kB)
Requirement already satisfied: SQLAlchemy[asyncio]>=1.4.49 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (2.0.23)
Requirement already satisfied: aiohttp<4.0.0,>=3.8.6 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (3.8.6)
Requirement already satisfied: aiostream<0.6.0,>=0.5.2 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (0.5.2)
Requirement already satisfied: beautifulsoup4<5.0.0,>=4.12.2 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (4.12.2)
Requirement already satisfied: dataclasses-json in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (0.5.14)
Requirement already satisfied: deprecated>=1.2.9.3 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (1.2.14)
Requirement already satisfied: fsspec>=2023.5.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (2023.10.0)
Requirement already satisfied: httpx in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (0.24.1)
Requirement already satisfied: nest-asyncio<2.0.0,>=1.5.8 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (1.5.8)
Requirement already satisfied: nltk<4.0.0,>=3.8.1 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (3.8.1)
Requirement already satisfied: numpy in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (1.24.4)
Requirement already satisfied: openai>=1.1.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (1.3.5)
Requirement already satisfied: pandas in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (2.0.3)
Requirement already satisfied: tenacity<9.0.0,>=8.2.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (8.2.3)
Requirement already satisfied: tiktoken>=0.3.3 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (0.5.1)
Requirement already satisfied: typing-extensions>=4.5.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (4.8.0)
Requirement already satisfied: typing-inspect>=0.8.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (0.8.0)
Requirement already satisfied: urllib3<2 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from llama_index<0.9.6) (1.26.18)
Requirement already satisfied: attrs>=17.3.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.6->llama_index<0.9.6) (23.1.0)
Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.6->llama_index<0.9.6) (3.3.2)
Requirement already satisfied: multidict<7.0,>=4.5 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.6->llama_index<0.9.6) (6.0.4)
Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.6->llama_index<0.9.6) (4.0.3)
Requirement already satisfied: yarl<2.0,>=1.0 in /home/loganm/.cache/pypoetry/virtualenvs/llama-index-4a-wkI5X-py3.11/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.6->llama_index<0.9.6) (1.9.2)
```

--------------------------------

### Instantiate PremAI Client with System Prompt

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/premai.ipynb

Initializes the PremAI client with a project ID and a custom system prompt override.

```python
chat = PremAI(project_id=8, system_prompt="Act like nemo fish")
```

--------------------------------

### Install LlamaIndex version 0.9.7 or higher

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/ingestion/async_ingestion_pipeline.ipynb

Install the minimum version of LlamaIndex required for improved async metadata extraction in pipelines. Restart notebook after installation.

```python
!pip install "llama_index>=0.9.7"
```

--------------------------------

### Install LlamaIndex and Weaviate Client

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/WeaviateIndex_auto_retriever.ipynb

Install the core llama-index library and the weaviate-client package.

```python
!pip install llama-index weaviate-client
```

--------------------------------

### Install llmsherpa dependency

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-smart-pdf-loader/README.md

Install the required llmsherpa library.

```shell
pip install llmsherpa
```

--------------------------------

### Install llama-index-readers-remote-depth

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/readers/llama-index-readers-remote-depth/README.md

Install the RemoteDepthReader package using pip.

```bash
pip install llama-index-readers-remote-depth

```

--------------------------------

### Initialize and Use RedisIndexStore

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/module_guides/storing/index_stores.md

Connect to Redis via host, port, and namespace, wrap the store in a StorageContext, and build or load a VectorStoreIndex.

```python
from llama_index.storage.index_store.redis import RedisIndexStore
from llama_index.core import VectorStoreIndex

# create (or load) docstore and add nodes
index_store = RedisIndexStore.from_host_and_port(
    host="127.0.0.1", port="6379", namespace="llama_index"
)

# create storage context
storage_context = StorageContext.from_defaults(index_store=index_store)

# build index
index = VectorStoreIndex(nodes, storage_context=storage_context)

# or alternatively, load index
from llama_index.core import load_index_from_storage

index = load_index_from_storage(storage_context)
```

--------------------------------

### Create ephemeral Chroma collection

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/chroma_auto_retriever.ipynb

Initializes an EphemeralClient and creates a new Chroma collection named 'quickstart'. Shows the telemetry output emitted upon creation.

```python
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")
```

```text
Output:
INFO:chromadb.telemetry.posthog:Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.
Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.

```

--------------------------------

### Install llama-index-node-parser-topic

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/node_parser/llama-index-node-parser-topic/README.md

Install the TopicNodeParser package using pip.

```shell
pip install llama-index-node-parser-topic

```

--------------------------------

### Initialize FaissVectorStore and FaissMapVectorStore

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/community/integrations/vector_stores.md

Demonstrates initializing basic FaissVectorStore and FaissMapVectorStore for update/delete support, followed by persisting to disk.

```python
import faiss
from llama_index.vector_stores.faiss import FaissVectorStore

# create faiss index
d = 1536
faiss_index = faiss.IndexFlatL2(d)

# construct vector store
vector_store = FaissVectorStore(faiss_index)

# if update/delete functionality is needed you can leverage the FaissMapVectorStore

d = 1536
faiss_index = faiss.IndexFlatL2(d)
id_map_index = faiss.IndexIDMap2(faiss_index)
vector_store = FaissMapVectorStore(id_map_index)

...

# NOTE: since faiss index is in-memory, we need to explicitly call
#       vector_store.persist() or storage_context.persist() to save it to disk.
#       persist() takes in optional arg persist_path. If none give, will use default paths.
storage_context.persist()
```

--------------------------------

### Install llama-index-llms-bedrock-converse

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/llms/llama-index-llms-bedrock-converse/README.md

Install the required packages using pip.

```bash
%pip install llama-index-llms-bedrock-converse
!pip install llama-index
```

--------------------------------

### Install trulens-eval

Source: https://github.com/run-llama/llama_index/blob/main/docs/src/content/docs/framework/community/integrations/trulens.md

Install the TruLens evaluation package from PyPI.

```sh
pip install trulens-eval
```

--------------------------------

### Initialize MoorchehVectorStore and query index

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-moorcheh/README.md

Demonstrates setting up `MoorchehVectorStore` with an API key and namespace, creating a `VectorStoreIndex` from loaded documents, and executing a search query.

```python
from llama_index.core import VectorStoreIndex
from llama_index.llama_index_integrations.vector_stores.llama_index_vector_stores_moorcheh.llama_index.vector_stores-moorcheh import base, init, utils

api_key = os.environ["MOORCHEH_API_KEY"]

documents = SimpleDirectoryReader("./your-directory").load_data()
__all__ = ["MoorchehVectorStore"]

# Creates a Moorcheh Vector Store with the following parameters
# For text-based namespaces, set namespace_type to "text" and vector_dimension to None
# For vector-based namespaces, set namespace_type to "vector" and vector_dimension to the dimension of your uploaded vectors
vector_store = MoorchehVectorStore(api_key=api_key, namespace="llamaindex_moorcheh", namespace_type="text", vector_dimension=None, add_sparse_vector=False, batch_size=100)

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

query_engine = index.as_query_engine()
response = query_engine.query("Which company has had the highest revenue in 2025 and why?")

display(Markdown(f"<b>{response}</b>"))
print("\n\n================================\n\n", response, "\n\n================================\n\n")
```

--------------------------------

### Initialize Gel Cloud project

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/gel.ipynb

Initialize a Gel project connected to a remote Gel Cloud instance.

```bash
gel project init --server-instance <org-name>/<instance-name>
```

--------------------------------

### Install required packages

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/observability/PromptLayerHandler.ipynb

Installs llama-index and promptlayer dependencies.

```python
!pip install llama-index
!pip install promptlayer
```

--------------------------------

### Install llama-index-node-parser-slide

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/node_parsers/slide_parser.ipynb

Install the SlideNodeParser integration package for LlamaIndex.

```python
%pip install llama-index-node-parser-slide
```

--------------------------------

### Install llama-index and qdrant_client Packages

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/Qdrant_using_qdrant_filters.ipynb

Install the core LlamaIndex package and the official Qdrant client library.

```python
!pip3 install llama-index qdrant_client
```

--------------------------------

### Install llama-index-llms-openrouter

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/openrouter.ipynb

Install the OpenRouter integration package for LlamaIndex.

```python
%pip install llama-index-llms-openrouter
```

--------------------------------

### Install llama-index-llms-rungpt

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/rungpt.ipynb

Installs the RunGPT integration package for LlamaIndex.

```python
%pip install llama-index-llms-rungpt
```

--------------------------------

### Create directory and download sample restaurant images

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/multi_modal/gemini.ipynb

Creates a local directory and downloads sample restaurant images for multimodal processing.

```python
from pathlib import Path

input_image_path = Path("google_restaurants")
if not input_image_path.exists():
    Path.mkdir(input_image_path)
```

```bash
!curl -sL "https://docs.google.com/uc?export=download&id=1Pg04p6ss0FlBgz00noHAOAJ1EYXiosKg" -o ./google_restaurants/miami.png
!curl -sL "https://docs.google.com/uc?export=download&id=1dYZy17bD6pSsEyACXx9fRMNx93ok-kTJ" -o ./google_restaurants/orlando.png
!curl -sL "https://docs.google.com/uc?export=download&id=1ShPnYVc1iL_TA1t7ErCFEAHT74-qvMrn" -o ./google_restaurants/sf.png
!curl -sL "https://docs.google.com/uc?export=download&id=1WjISWnatHjwL4z5VD_9o09ORWhRJuYqm" -o ./google_restaurants/toronto.png
```

--------------------------------

### Install llama-index-llms-qianfan

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/qianfan.ipynb

Install the Qianfan integration package for LlamaIndex.

```python
%pip install llama-index-llms-qianfan
```

--------------------------------

### Initialize QdrantClient

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/Qdrant_metadata_filter.ipynb

Creates an in-memory Qdrant client for lightweight local experiments without requiring an external Qdrant deployment.

```python
import qdrant_client
from llama_index.core import VectorStoreIndex
from llama_index.vector_stores.qdrant import QdrantVectorStore

client = qdrant_client.QdrantClient(
    # you can use :memory: mode for fast and light-weight experiments,
    # it does not require to have Qdrant deployed anywhere
    # but requires qdrant-client >= 1.1.1
    location=":memory:"
    # otherwise set Qdrant instance address with:
    # uri="http://<host>:<port>"
    # set API KEY for Qdrant Cloud
    # api_key="<qdrant-api-key>",
)
```

--------------------------------

### Configure SimpleChatEngine with MARKETING_WRITING_ASSISTANT

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/chat_engine/chat_engine_personality.ipynb

Set system_prompt to MARKETING_WRITING_ASSISTANT to generate marketing-focused copy.

```python
from llama_index.core.chat_engine import SimpleChatEngine
from llama_index.core.prompts.system import MARKETING_WRITING_ASSISTANT

chat_engine = SimpleChatEngine.from_defaults(
    system_prompt=MARKETING_WRITING_ASSISTANT
)
response = chat_engine.chat(
    "Say something profound and romantic about fourth of July"
)
print(response)
```

```text
Output:
 Fourth of July is a time to celebrate the freedom and independence of our nation. It's a time to reflect on the beauty of our country and the courage of those who fought for our freedom. It's a time to come together and appreciate the beauty of our nation and the people who make it so special.

```

--------------------------------

### Install llama-index-llms-anthropic

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/anthropic.ipynb

Install the Anthropic integration package for LlamaIndex.

```python
%pip install llama-index-llms-anthropic
```

--------------------------------

### Instantiate RouterQueryEngine with choices

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/low_level/router.ipynb

Sets up choices and instantiates the RouterQueryEngine with vector and summary query engines.

```python
choices = [
    (
        "Useful for answering questions about specific sections of the Llama 2"
        " paper"
    ),
    "Useful for questions that ask for a summary of the whole paper",
]

router_query_engine = RouterQueryEngine(
    query_engines=[vector_query_engine, summary_query_engine],
    choice_descriptions=choices,
    verbose=True,
    router_prompt=router_prompt1,
    llm=OpenAI(model="gpt-4"),
)
```

--------------------------------

### Install required packages

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/evaluation/Deepeval.ipynb

Install llama-index and deepeval dependencies.

```python
!pip install -q -q llama-index
!pip install -U -q deepeval
```

--------------------------------

### Install Gel and LlamaIndex packages

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/vector_stores/gel.ipynb

Install the Gel client, LlamaIndex Gel vector store integration, and core LlamaIndex packages.

```python
! pip install gel llama-index-vector-stores-gel
```

```python
! pip install llama-index
```

--------------------------------

### Install llama-index-readers-twitter

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/data_connectors/TwitterDemo.ipynb

Installs the Twitter reader package for LlamaIndex.

```python
%pip install llama-index-readers-twitter
```

--------------------------------

### Install llama-index-readers-milvus

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/data_connectors/MilvusReaderDemo.ipynb

Install the Milvus reader package for LlamaIndex.

```python
%pip install llama-index-readers-milvus
```

--------------------------------

### Initialize MyQueryEngine instance

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/low_level/response_synthesis.ipynb

Instantiates MyQueryEngine using configured retriever, prompt template, LLM, and child node threshold.

```python
query_engine = MyQueryEngine(retriever, qa_prompt, llm, num_children=10)
```

--------------------------------

### Initialize Contextual LLM and run completion

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/llms/llama-index-llms-contextual/README.md

Instantiate the Contextual LLM with a model and API key, then call complete with a prompt.

```python
from llama_index.llms.contextual import Contextual

llm = Contextual(model="contextual-clm", api_key="your_api_key")

response = llm.complete("Explain the importance of Grounded Language Models.")
```

--------------------------------

### Install LlamaIndex

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/agent/agent_with_structured_output.ipynb

Installs the llama-index package using pip.

```python
! pip install llama-index
```

--------------------------------

### Install required packages for MistralRS integration

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/llm/mistral_rs.ipynb

Installs the required LlamaIndex core, reader, MistralRS, and Hugging Face packages. MistralRS requires cargo to be installed beforehand.

```python
%pip install llama-index-core
%pip install llama-index-readers-file
%pip install llama-index-llms-mistral-rs
%pip install llama-index-llms-huggingface
```

--------------------------------

### Configure sample .env file for Astra DB and OpenAI

Source: https://github.com/run-llama/llama_index/blob/main/docs/examples/tools/cassandra.ipynb

Example `.env` configuration providing Astra DB connection parameters and an OpenAI API key.

```bash
# Connection to Astra:
ASTRA_DB_DATABASE_ID=a1b2c3d4-...
ASTRA_DB_APPLICATION_TOKEN=AstraCS:...
ASTRA_DB_KEYSPACE=notebooks

# Also set 
OPENAI_API_KEY=sk-....
```

--------------------------------

### Install llama-index-tools-neo4j

Source: https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-neo4j/README.md

Install the Neo4j tools package via pip.

```bash
pip install llama-index-tools-neo4j

```
Tokens:
Raw