fetch relevance from vector store

may be in future have a relevance threshold.
added Qdrant url to env

Dockerfile

@@ -17,6 +17,6 @@ COPY api .
 EXPOSE 8080
 
 ENV OPENAI_API_KEY=zzz
-ENV QDRANT_API_KEY=yyy
+ENV QDRANT_URL="https://32f125d3-5ab1-4058-a10a-bd38a1ebd647.us-east-1-0.aws.cloud.qdrant.io"
 # Start the application using Uvicorn
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]

api/db/vector_store.py

@@ -4,8 +4,9 @@ from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Qdrant
 
 embeddings = OpenAIEmbeddings()
-client = QdrantClient(url="https://32f125d3-5ab1-4058-a10a-bd38a1ebd647.us-east-1-0.aws.cloud.qdrant.io",
+client = QdrantClient(url=os.getenv("QDRANT_URL"),
                                     api_key=os.getenv("QDRANT_API_KEY"))
 
 def get_instance(collection: str = "test"):
     return Qdrant(client=client,collection_name=collection,embeddings=embeddings)
+

api/routes/search.py

@@ -41,10 +41,10 @@ async def answer(name: str, query: str):
     """
     _db = vector_store.get_instance(name)
     print(query)
-    docs = _db.similarity_search(query=query)
+    docs = _db.similarity_search_with_relevance_scores(query=query)
     print(docs)
-    answer = _chain.run(input_documents=docs, question=query)
-    return JSONResponse(status_code=200, content={"answer": answer, "files": [d.metadata["file"] for d in docs]}) 
+    answer = _chain.run(input_documents=[tup[0] for tup in docs], question=query)
+    return JSONResponse(status_code=200, content={"answer": answer, "file_score": [[f"{d[0].metadata['file']} : {d[0].metadata['page']}", d[1]] for d in docs]}) 
 
 async def generate_documents(file: UploadFile, fileName: str):
     num=0