Upload 2 files

app.py

@@ -0,0 +1,54 @@
+# fjk3hxK9MNC8h1X4m7zCjmcn4sCtJhur_Cg65csBw1OZeUwdktZwbQ
+from dotenv import load_dotenv
+import streamlit as st
+
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from langchain.vectorstores import Qdrant
+from langchain.embeddings.openai import OpenAIEmbeddings
+import qdrant_client
+import os
+
+def get_vector_store():
+    
+    client = qdrant_client.QdrantClient(
+        os.getenv("QDRANT_HOST"),
+        api_key=os.getenv("QDRANT_API_KEY")
+    )
+    
+    embeddings = OpenAIEmbeddings()
+
+    vector_store = Qdrant(
+        client=client, 
+        collection_name=os.getenv("QDRANT_COLLECTION_NAME"), 
+        embeddings=embeddings,
+    )
+    
+    return vector_store
+
+def main():
+    load_dotenv()
+    
+    st.set_page_config(page_title="Ask Qdrant")
+    st.header("Ask your remote database 💬")
+    
+    # create vector store
+    vector_store = get_vector_store()
+    
+    # create chain 
+    qa = RetrievalQA.from_chain_type(
+        llm=OpenAI(),
+        chain_type="stuff",
+        retriever=vector_store.as_retriever()
+    )
+
+    # show user input
+    user_question = st.text_input("Ask a question about your PDF:")
+    if user_question:
+        st.write(f"Question: {user_question}")
+        answer = qa.run(user_question)
+        st.write(f"Answer: {answer}")
+    
+        
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,14 @@
+langchain
+python-dotenv
+streamlit
+openai
+qdrant-client
+tiktoken
+
+
+# uncomment to use huggingface llms
+# huggingface-hub==0.14.1
+
+# uncomment to use instructor embeddings
+# InstructorEmbedding==1.0.1
+# sentence-transformers==2.2.2