Vector Search

pip install chromadb langchain-chroma

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

# Create embeddings model
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

# Create vector store and add documents
vectorstore = Chroma.from_documents(
    documents=chunks,
    embedding=embeddings,
    persist_directory="./chroma_db",
    collection_name="my_docs"
)

# Search for similar documents
results = vectorstore.similarity_search(
    "How do I reset my password?",
    k=5
)

for doc in results:
    print(doc.page_content[:200])

pip install pinecone langchain-pinecone

from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAIEmbeddings
from pinecone import Pinecone

# Initialize Pinecone
pc = Pinecone(api_key="your-api-key")

# Create vector store
vectorstore = PineconeVectorStore.from_documents(
    documents=chunks,
    embedding=OpenAIEmbeddings(),
    index_name="my-rag-index"
)

# Search with metadata filtering
results = vectorstore.similarity_search(
    "deployment guide",
    k=5,
    filter={"department": "engineering"}
)

from langchain_weaviate import WeaviateVectorStore

vectorstore = WeaviateVectorStore(
    client=weaviate_client,
    index_name="Documents",
    text_key="content",
    embedding=embeddings
)

# Hybrid search: combines vector + keyword (BM25)
retriever = vectorstore.as_retriever(
    search_type="hybrid",
    search_kwargs={
        "k": 5,
        "alpha": 0.5  # 0 = pure keyword, 1 = pure vector
    }
)

# Search only in specific documents or categories
results = vectorstore.similarity_search(
    "API authentication",
    k=5,
    filter={
        "source_type": "documentation",
        "department": {"$in": ["engineering", "security"]},
        "last_updated": {"$gte": "2025-01-01"}
    }
)