Docx Knowledge Base
The DocxKnowledgeBase reads local docx files, 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.docx import DocxKnowledgeBase
from bitca.vectordb.pgvector import PgVector
knowledge_base = DocxKnowledgeBase(
path="data/docs",
# Table name: ai.docx_documents
vector_db=PgVector(
table_name="docx_documents",
db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
),
)
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("Ask me about something from the knowledge base")
Params
path
Union[str, Path]
-
Path to docx files. Can point to a single docx file or a directory of docx files.
formats
List[str]
[".doc", ".docx"]
Formats accepted by this knowledge base.
reader
DocxReader
DocxReader()
A DocxReader
that converts the docx 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.
Last updated