new cache

app.py

@@ -18,21 +18,8 @@ def qa(query):
     texts = text_splitter.split_documents(docs)
     embeddings = HuggingFaceEmbeddings()
     vectordb = Chroma.from_documents(documents=texts,embedding=embeddings)
-    qa = RetrievalQA.from_chain_type(llm=llm(), chain_type="stuff",retriever=vectordb.as_retriever(search_type="mmr", search_kwargs={'fetch_k': 30}), return_source_documents=True)
-    return qa
-def main():
-    # pdf_folder_path = "./PDFfiles"
-    # loader = PyPDFDirectoryLoader(pdf_folder_path)
-    # docs = loader.load()
-    # text_splitter = RecursiveCharacterTextSplitter (chunk_size=1000, chunk_overlap=200)
-    # texts = text_splitter.split_documents(docs)
-    # embeddings = HuggingFaceEmbeddings()
-    # vectordb = Chroma.from_documents(documents=texts,embedding=embeddings)
-    # llm = HuggingFaceHub(repo_id="google/flan-t5-small", model_kwargs={"temperature":0,"max_length":200}, huggingfacehub_api_token="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") # type: ignore
-    # qa = RetrievalQA.from_chain_type(llm=llm(), chain_type="stuff",retriever=vectordb.as_retriever(search_type="mmr", search_kwargs={'fetch_k': 30}), return_source_documents=True)
-    query = st.text_input("Ask a question: ")
-    # qa(inputs=query,return_only_outputs=True)
-    result = qa({"query": query})
-    st.write(result["result"])
-    st.write(result["source_documents"][0])
-main()
+    return RetrievalQA.from_chain_type(llm=llm(), chain_type="stuff",retriever=vectordb.as_retriever(search_type="mmr", search_kwargs={'fetch_k': 30}), return_source_documents=True)
+query = st.text_input("Ask a question: ")
+result = qa({"query": query})
+st.write(result["result"])
+st.write(result["source_documents"][0])