comment source

app.py

@@ -196,6 +196,11 @@ def set_custom_prompt():
                                                                               'chat_history'])
     return prompt
 
+@st.cache_resource
+def create_db(text,embeddings):
+    return FAISS.from_texts(text, embeddings)
+
+
 @st.cache_resource
 def load_embeddings():
     embeddings = HuggingFaceEmbeddings(model_name = "thenlper/gte-base",
@@ -241,7 +246,7 @@ def main():
         text = ""
         for page in pdf_reader.pages:
             text += page.extract_text()
-        db = FAISS.from_texts(text, embeddings)
+        db = create_db(text,embeddings)
         qa_chain = ConversationalRetrievalChain(
             retriever =db.as_retriever(search_type="similarity_score_threshold", search_kwargs={'k':2,  "score_threshold": 0.7}), 
             question_generator=question_generator,
@@ -268,7 +273,7 @@ def main():
 
             response = qa_chain({'question': query})
 
-            url_list = set([i.metadata['source']  for i in response['source_documents']])
+            # url_list = set([i.metadata['source']  for i in response['source_documents']])
             #print(f"condensed quesion : {question_generator.run({'chat_history': response['chat_history'], 'question' : query})}")
             
             with st.chat_message("assistant"):
@@ -280,10 +285,10 @@ def main():
             # Add assistant response to chat history
             st.session_state.messages.append({"role": "assistant", "content": response['answer']})
 
-            with st.expander("See the related documents"):
-                for count, url in enumerate(url_list):
-                    #url_reg = regex_source(url)
-                    st.write(str(count+1)+":", url)
+            # with st.expander("See the related documents"):
+            #     for count, url in enumerate(url_list):
+            #         #url_reg = regex_source(url)
+            #         st.write(str(count+1)+":", url)
 
         clear_button = st.button("Start new convo")
         if clear_button :