Weaviate Vector Database

Use Weaviate as a vector database for your Knowledge Base.

Follow steps mentioned in Weaviate setup guide to setup Weaviate.

Setup

Install weaviate packages

1uv pip install weaviate-client

Run weaviate

1docker run -d \
2  -p 8080:8080 \
3  -p 50051:50051 \
4  --name weaviate \
5  cr.weaviate.io/semitechnologies/weaviate:1.28.4

1./cookbook/scripts/run_weaviate.sh

Example

1from kern.agent import Agent
2from kern.knowledge.knowledge import Knowledge
3from kern.vectordb.search import SearchType
4from kern.vectordb.weaviate import Distance, VectorIndex, Weaviate
5
6vector_db = Weaviate(
7    collection="recipes",
8    search_type=SearchType.hybrid,
9    vector_index=VectorIndex.HNSW,
10    distance=Distance.COSINE,
11    local=True,  # Set to False if using Weaviate Cloud and True if using local instance
12)
13# Create knowledge base
14knowledge_base = Knowledge(
15    vector_db=vector_db,
16)
17
18# Create and use the agent
19agent = Agent(
20    knowledge=knowledge_base,
21    search_knowledge=True,
22)
23
24if __name__ == "__main__":
25    knowledge_base.insert(
26        url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
27    )
28
29    agent.print_response("How to make Thai curry?", markdown=True)

Async Support ⚡

Weaviate also supports asynchronous operations, enabling concurrency and leading to better performance.

1import asyncio
2
3from kern.agent import Agent
4from kern.knowledge.knowledge import Knowledge
5from kern.vectordb.search import SearchType
6from kern.vectordb.weaviate import Distance, VectorIndex, Weaviate
7
8vector_db = Weaviate(
9    collection="recipes_async",
10    search_type=SearchType.hybrid,
11    vector_index=VectorIndex.HNSW,
12    distance=Distance.COSINE,
13    local=True,  # Set to False if using Weaviate Cloud and True if using local instance
14)
15
16# Create knowledge base
17knowledge_base = Knowledge(
18    vector_db=vector_db,
19)
20
21agent = Agent(
22    knowledge=knowledge_base,
23    search_knowledge=True,
24)
25
26if __name__ == "__main__":
27    # Load knowledge base asynchronously
28    asyncio.run(knowledge_base.ainsert(
29            url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
30        )
31    )
32
33    # Create and use the agent asynchronously
34    asyncio.run(agent.aprint_response("How to make Tom Kha Gai", markdown=True))

Tip

Weaviate's async capabilities leverage WeaviateAsyncClient to provide non-blocking vector operations. This is particularly valuable for applications requiring high concurrency and throughput.

Weaviate Params

Parameter	Type	Description	Default
`wcd_url`	`Optional[str]`	Weaviate Cloud URL (or use WCD_URL env var)	`None`
`wcd_api_key`	`Optional[str]`	Weaviate Cloud API key (or use WCD_API_KEY env var)	`None`
`client`	`Optional[weaviate.WeaviateClient]`	Pre-configured Weaviate client	`None`
`local`	`bool`	Whether to use a local Weaviate instance	`False`
`collection`	`str`	Name of the Weaviate collection	`"default"`
`vector_index`	`VectorIndex`	Type of vector index (HNSW, FLAT, DYNAMIC)	`VectorIndex.HNSW`
`distance`	`Distance`	Distance metric (COSINE, DOT, etc.)	`Distance.COSINE`
`embedder`	`Optional[Embedder]`	Embedder to use for generating embeddings	`OpenAIEmbedder()`
`search_type`	`SearchType`	Search type (vector, keyword, hybrid)	`SearchType.vector`
`reranker`	`Optional[Reranker]`	Reranker to refine search results	`None`
`hybrid_search_alpha`	`float`	Weighting factor for hybrid search	`0.5`