v0.2.0

src/indexer.py

@@ -7,7 +7,7 @@ from langchain.retrievers.self_query.base import SelfQueryRetriever
 from langchain.chains.query_constructor.base import AttributeInfo
 from llm.llmFactory import LLMFactory
 
-model_name = "BAAI/bge-base-en"
+model_name = "BAAI/bge-large-en-v1.5"
 encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
 
 embedding = HuggingFaceBgeEmbeddings(

src/main.py

@@ -41,6 +41,9 @@ api_base="/api/v1"
 @app.post(api_base+"/getMatchingDocs")
 async def get_matching_docs(inStr: str ) -> Any:
     """
+    Gets the query embeddings and uses metadata appropriately and gets the matching docs for query
+    TODO: Add parameter for type of query and number of docs to return
+    TODO: Add parameter to return the source information as well
     """
     return getRelevantDocs(inStr)