all

app.py

@@ -17,31 +17,26 @@ from langchain.vectorstores import Chroma
 from langchain.chains import ConversationalRetrievalChain
 
 def loading_pdf():
+    print("loading_pdf")
     return "Loading..."
 
 def pdf_changes(pdf_doc, open_ai_key):
+    print("pdf_change")
     if openai_key is not None:
         os.environ['OPENAI_API_KEY'] = open_ai_key
         loader = OnlinePDFLoader(pdf_doc.name)
-        print('loader\n\n\n')
         print(loader)
         documents = loader.load()
-        print('documents\n\n\n')
         print(documents)
         text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-        print('splitter\n\n\n')
         print(text_splitter)
         texts = text_splitter.split_documents(documents)
-        print('texts\n\n\n')
         print(texts)
         embeddings = OpenAIEmbeddings()
-        print('embeddings\n\n\n')
         print(embeddings)
         db = Chroma.from_documents(texts, embeddings)
-        print('db\n\n\n')
         print(db)
         retriever = db.as_retriever()
-        print('retriever\n\n\n')
         print(retriever)
         global qa
         qa = ConversationalRetrievalChain.from_llm(
@@ -59,15 +54,11 @@ def add_text(history, text):
 
 def bot(history):
     response = infer(history[-1][0], history)
-    print('bot response:')
-    print(response)
     history[-1][1] = ""
 
     for character in response:
         history[-1][1] += character
-        print("history")
         time.sleep(0.05)
-        print(history)
         yield history
 
 
@@ -83,8 +74,6 @@ def infer(question, history):
     query = question
     result = qa({"question": query, "chat_history": chat_history})
     #print(result)
-    print("infer result")
-    print(result)
     return result["answer"]
 
 css="""