vector-databases

# Vector Databases

Master vector storage and retrieval for AI applications.

## Quick Start

### Chroma (Local Development)
```python
import chromadb
from chromadb.utils import embedding_functions

# Initialize client
client = chromadb.Client()  # In-memory
# client = chromadb.PersistentClient(path="./chroma_db")  # Persistent

# Create collection with embedding function
embedding_fn = embedding_functions.SentenceTransformerEmbeddingFunction(
    model_name="all-MiniLM-L6-v2"
)

collection = client.create_collection(
    name="documents",
    embedding_function=embedding_fn
)

# Add documents
collection.add(
    documents=["Document 1 text", "Document 2 text"],
    metadatas=[{"source": "file1"}, {"source": "file2"}],
    ids=["doc1", "doc2"]
)

# Query
results = collection.query(
    query_texts=["search query"],
    n_results=5
)
```

### Pinecone (Cloud Production)
```python
from pinecone import Pinecone, ServerlessSpec

# Initialize
pc = Pinecone(api_key="YOUR_API_KEY")

# Create index
pc.create_index(
    name="documents",
    dimension=1536,  # OpenAI embedding dimension
    metric="cosine",
    spec=ServerlessSpec(cloud="aws", region="us-west-2")
)

index = pc.Index("documents")

# Upsert vectors
index.upsert(vectors=[
    {"id": "doc1", "values": embedding1, "metadata": {"text": "..."}},
    {"id": "doc2", "values": embedding2, "metadata": {"text": "..."}}
])

# Query
results = index.query(
    vector=query_embedding,
    top_k=10,
    include_metadata=True
)
```

### Weaviate
```python
import weaviate
from weaviate.classes.config import Configure, Property, DataType

# Connect
client = weaviate.connect_to_local()  # or connect_to_wcs()

# Create collection (class)
collection = client.collections.create(
    name="Document",
    vectorizer_config=Configure.Vectorizer.text2vec_openai(),
    properties=[
        Property(name="content", data_type=DataType.TEXT),
        Property(name="source", data_type=DataType.TEXT)
    ]
)

# Add objects
collection.data.in