Vector Store: Qdrant

Qdrant is a vector similarity search engine that provides a production-ready service with a convenient API for storing, searching, and managing embeddings.

1. Configuration Parameters

Specify your Qdrant configuration within vector_store_params:

Parameter	Type	Default	Description
`vector_store_type`	`string`	`"QdrantVectorStore"`	Identifier of the Qdrant vector store wrapper.
`url`	`string`	`None`	The HTTP endpoint for your hosted Qdrant cluster.
`api_key`	`string`	`None`	Authentication key.
`collection_name`	`string`	`None`	The Qdrant collection name to store the embeddings in.

2. Configuration Example

Here is a Python example configuring a ChatBot with Qdrant:

from aih import ChatBot
 
qdrant_config = {
    "vector_store_type": "QdrantVectorStore",
    "url": "https://your-qdrant-instance.gcp.qdrant.io:6333",
    "api_key": "your_qdrant_api_key",
    "collection_name": "aih_docs_collection"
}
 
chatbot = ChatBot.pdf_chat(
    input_files=["./brochure.pdf"],
    vector_store_params=qdrant_config
)

Weaviate Pinecone