Update app.py

app.py

@@ -23,9 +23,10 @@ from langchain.prompts import (
     MessagesPlaceholder,
     SystemMessagePromptTemplate,
 )
+from langchain.schema import AIMessage,HumanMessage
 documents=[]
 path='./bios/'
-# path='./augBios/'
+
 for file in os.listdir(path):
     loader = TextLoader(f'{path}{file}',encoding='unicode_escape')
     # loader.load()[0].metadata['category']='biography'
@@ -37,7 +38,6 @@ print(len(documents))
 text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=0)
 texts = text_splitter.split_documents(documents)
 
-# embeddings = OpenAIEmbeddings()
 embeddings = CohereEmbeddings(model='embed-english-v3.0')
 docsearch = Chroma.from_documents(texts, embeddings)
 
@@ -45,66 +45,25 @@ qa = RetrievalQA.from_chain_type(llm=Cohere(model='command'), chain_type="stuff"
     retriever=docsearch.as_retriever(search_kwargs={'k':1}),return_source_documents=True)
 
 def predict(message, history):
-    # history_langchain_format = []
-    # for human, ai in history:
-    #     history_langchain_format.append(HumanMessage(content=human))
-    #     history_langchain_format.append(AIMessage(content=ai))
-    # history_langchain_format.append(HumanMessage(content=message))
-    # gpt_response = llm(history_langchain_format)
-    # return gpt_response.content
+    history_langchain_format = []
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+    history_langchain_format.append(HumanMessage(content=message))
+    gpt_response = qa({'query':history_langchain_format})
+    return gpt_response['result']
     
-    message=message+'? just the book title-Author'
-    result = qa({"query": message})
-    # r1=docsearch.similarity_search_with_score(query=q,k=3)
-    # print([(item[-2].metadata,item[-1]) for item in r1],\
-    #       '\n\n',result['result'],f'|| {result["source_documents"][0].metadata}','\n*****\n')
-    if result['result'] not in ["I don't know","I don't know."]:
-        return result['result']+f'\n---\nAmazon Kindle ebook description is:\n {result["source_documents"][0].page_content}'+\
-        f'\nfrom this file: {result["source_documents"][0].metadata}'
-    else:
-        return result['result']
-'''This is code used for with memory chat'''    
-# text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
-# texts = text_splitter.split_documents(documents)
-
-# # embeddings = OpenAIEmbeddings()
-# embeddings = CohereEmbeddings(model='embed-english-v3.0')
-# docsearch = Chroma.from_documents(texts, embeddings)
-# memory=ConversationSummaryMemory(
-#     llm=Cohere(model='command'), memory_key="chat_history", return_messages=True
-# )
-# qa = ConversationalRetrievalChain.from_llm(llm=Cohere(model='command'), \
-#     retriever=docsearch.as_retriever(),return_source_documents=True,memory=memory)
+    # message=message+'? just the book title-Author'
+    # result = qa({"query": message})
+    # # r1=docsearch.similarity_search_with_score(query=q,k=3)
+    # # print([(item[-2].metadata,item[-1]) for item in r1],\
+    # #       '\n\n',result['result'],f'|| {result["source_documents"][0].metadata}','\n*****\n')
+    # if result['result'] not in ["I don't know","I don't know."]:
+    #     return result['result']+f'\n---\nAmazon Kindle ebook description is:\n {result["source_documents"][0].page_content}'+\
+    #     f'\nfrom this file: {result["source_documents"][0].metadata}'
+    # else:
+    #     return result['result']
 
-# def predict(message, history):
-#     # history_langchain_format = []
-#     # for human, ai in history:
-#     #     history_langchain_format.append(HumanMessage(content=human))
-#     #     history_langchain_format.append(AIMessage(content=ai))
-#     # history_langchain_format.append(HumanMessage(content=message))
-#     # gpt_response = llm(history_langchain_format)
-#     # return gpt_response.content
-    
-#     # message=message+'? just the book title-Autho'
-#     #---------
-#     # for human, ai in history:
-#     #     history_langchain_format.append(HumanMessage(content=human))
-#     #     history_langchain_format.append(AIMessage(content=ai))
-#     # history_langchain_format.append(HumanMessage(content=message))
-#     # gpt_response = llm(history_langchain_format)
-#     # return gpt_response.content
-#     #------------
-    
-#     result = qa(message)
-#     # r1=docsearch.similarity_search_with_score(query=q,k=3)
-#     # print([(item[-2].metadata,item[-1]) for item in r1],\
-#     #       '\n\n',result['result'],f'|| {result["source_documents"][0].metadata}','\n*****\n')
-#     if result['result'] not in ["I don't know","I don't know."]:
-#         return result['result']+f'\n---\nAmazon Kindle ebook description is:\n {result["source_documents"][0].page_content}'+\
-#         f'\nfrom this file: {result["source_documents"][0].metadata}'
-#     else:
-#         return result['result']    
-'''------'''
 gr.ChatInterface(predict,
     chatbot=gr.Chatbot(height='auto'),
     textbox=gr.Textbox(placeholder="Recommend a book on someone who..."),