### Local Development with Poetry

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Installs project dependencies and runs tests locally using Poetry. This is the recommended approach for development work.

```bash
poetry install
poetry run pytest
```

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

### Install vectordb-orm

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Installs the vectordb-orm package and its dependencies using pip. Ensure you have a vector database running before connecting.

```bash
pip install vectordb-orm
```

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

### Clone and Run vectordb-orm with Docker

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Clones the vectordb-orm repository, navigates into the directory, and starts the necessary services using Docker Compose. This is primarily for testing Milvus.

```bash
git clone https://github.com/piercefreeman/vectordb-orm.git
cd vectordb-orm
docker-compose up -d
```

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

### Insert and Query Data

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Demonstrates inserting a single object and performing batch insertion with a progress bar in vectordb-orm. It also shows basic filtering and similarity-based ordering in queries.

```Python
obj = MyObject(text="my_text", embedding=np.array([1.0]*128))
session.insert(obj)

obj = MyObject(text="my_text", embedding=np.array([1.0]*128))
session.insert_batch([obj], show_progress=True)

session = VectorSession(...)

# Perform a simple boolean query
results = session.query(MyObject).filter(MyObject.text == 'bar').limit(2).all()

# Rank results by their similarity to a given reference vector
query_vector = np.array([8.0]*128)
results = session.query(MyObject).filter(MyObject.text == 'bar').order_by_similarity(MyObject.embedding, query_vector).limit(2).all()
```

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

### Create Milvus Session

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Establishes a database session for Milvus using vectordb-orm. It involves connecting to Milvus and creating a collection based on a defined schema.

```Python
from pymilvus import Milvus, connections
from vectordb_orm import MilvusBackend, VectorSession

# Instantiate a Milvus session
session = VectorSession(MilvusBackend(Milvus()))
connections.connect("default", host="localhost", port="19530")
session.create_collection(MyObject)
```

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

### Create Pinecone Session

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Establishes a database session for Pinecone using vectordb-orm. It requires API key and environment variables for authentication and initializes the session.

```Python
from vectordb_orm import PineconeBackend, VectorSession

# Instantiate a Pinecone session
session = VectorSession(
    PineconeBackend(
        api_key=getenv("PINECONE_API_KEY"),
        environment=getenv("PINECONE_ENVIRONMENT"),
    )
)
session.create_collection(MyObject)
```

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

### Define Milvus Schema

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Defines a data schema for Milvus using vectordb-orm. It includes primary key, variable character field, and an embedding field with Milvus-specific indexing (Milvus_IVF_FLAT).

```Python
from vectordb_orm import VectorSchemaBase, EmbeddingField, VarCharField, PrimaryKeyField, Milvus_IVF_FLAT
import numpy as np

class MyObject(VectorSchemaBase):
    __collection_name__ = 'my_object_collection'

    id: int = PrimaryKeyField()
    text: str = VarCharField(max_length=128)
    embedding: np.ndarray = EmbeddingField(dim=128, index=Milvus_IVF_FLAT(cluster_units=128))
```

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

### Define Pinecone Schema

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Defines a data schema for Pinecone using vectordb-orm. It includes primary key, variable character field, and an embedding field with Pinecone-specific indexing (PineconeIndex with cosine similarity).

```Python
from vectordb_orm import VectorSchemaBase, EmbeddingField, VarCharField, PrimaryKeyField, PineconeIndex, PineconeSimilarityMetric
import numpy as np

class MyObject(VectorSchemaBase):
    __collection_name__ = 'my_object_collection'

    id: int = PrimaryKeyField()
    text: str = VarCharField(max_length=128)
    embedding: np.ndarray = EmbeddingField(dim=128, index=PineconeIndex(metric_type=PineconeSimilarityMetric.COSINE))
```

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

### Define Floating Point Embedding

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Specifies a floating-point embedding type for vectordb-orm, using numpy's default array type and a BIN_FLAT index.

```Python
embedding: np.ndarray = EmbeddingField(
    dim=128,
    index=BIN_FLAT()
)
```

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

### Define Binary Embedding

Source: https://github.com/piercefreeman/vectordb-orm/blob/main/README.md

Specifies a binary embedding type for vectordb-orm, using numpy's boolean type signature and a FLAT index.

```Python
embedding: np.ndarray[np.bool_] = EmbeddingField(
    dim=128,
    index=FLAT()
)
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.