Elsai VectorDB v1.1.0

ChromaDB, Pinecone, and Weaviate integrations.

INFO

v2.0 adds filter-based retrieval and as_retriever() for RAG workflows. See v2.0 docs.

Installation

pip install --extra-index-url https://core-packages.elsai.ai/root/elsai-vectordb/ elsai-vectordb==1.1.0

---

ChromaVectorDb

from elsai_vectordb.chromadb import ChromaVectorDb

db = ChromaVectorDb(persist_directory="./db")
db.create_if_not_exists(collection_name="my_docs")

db.add_document(
    document={
        "id": "001",
        "embeddings": [0.1, 0.2, 0.7],
        "page_content": "Sample document.",
        "metadatas": {"source": "report.pdf"},
    },
    collection_name="my_docs",
)

results = db.retrieve_document(
    collection_name="my_docs",
    embeddings=[0.1, 0.2, 0.7],
    k=5,
)

# CRUD (v1.1.0+)
db.update_document(document={...}, collection_name="my_docs")
db.delete_document(ids=["001"], collection_name="my_docs")
db.list_collections()
db.delete_collection(collection_name="my_docs")

---

PineconeVectorDb

from elsai_vectordb.pinecone import PineconeVectorDb

db = PineconeVectorDb(index_name="my-index", pinecone_api_key="your_key", dimension=1536)

db.add_document(
    document={"id": "001", "embeddings": [...], "page_content": "Text.", "metadatas": {}},
    namespace="my-ns",
)

results = db.retrieve_document(embeddings=[...], namespace="my-ns", k=5)

---

WeaviateVectorDb

from elsai_vectordb.weaviate import WeaviateVectorDb

db = WeaviateVectorDb(
    weaviate_url="https://your-instance.weaviate.network",
    weaviate_api_key="your_key",
    class_name="Document",
)
db.add_document(document={...})
results = db.retrieve_document(embeddings=[...], k=5)