S3 Text Knowledge Base

The S3TextKnowledgeBase reads text files from an S3 bucket, converts them into vector embeddings and loads them to a vector databse.

​Usage

We are using a local PgVector database for this example. Make sure it’s running

pip install textract

from bitca.knowledge.s3.text import S3TextKnowledgeBase
from bitca.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

knowledge_base = S3TextKnowledgeBase(
    bucket_name="bitca-public",
    key="recipes/recipes.docx",
    vector_db=PgVector(table_name="recipes", db_url=db_url),
)

Then use the knowledge_base with an Agent:

from bitca.agent import Agent
from knowledge_base import knowledge_base

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)
agent.knowledge.load(recreate=False)

agent.print_response("How to make Hummus?")

​Params

Parameter	Type	Default	Description
formats	List[str]	[".doc", ".docx"]	Formats accepted by this knowledge base.
reader	S3TextReader	S3TextReader()	A S3TextReader that converts the Text files into Documents for the vector database.
vector_db	VectorDb	-	Vector Database for the Knowledge Base.
num_documents	int	5	Number of documents to return on search.
optimize_on	int	-	Number of documents to optimize the vector db on.
chunking_strategy	ChunkingStrategy	FixedSizeChunking	The chunking strategy to use.