Update app.py

app.py

@@ -13,21 +13,71 @@ os.environ["OPENAI_API_KEY"] = "sk-D30n0meArZqHhnMqe5TeT3BlbkFJUjqqnbFL1D5GDLK0k
 st.set_page_config(page_title="ChefGT", page_icon=":robot:")
 st.header("AidFinder")
 
+from langchain.chat_models import ChatOpenAI
+from langchain.chains.question_answering import load_qa_chain
+
+llm = ChatOpenAI(
+  openai_api_key=os.environ.get("OPENAI_API_KEY"),
+  model='gpt-3.5-turbo-16k',
+  temperature=0,
+  streaming=True
+)
+
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from langchain.document_loaders import TextLoader
+from langchain.document_loaders import PyPDFLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains.question_answering import load_qa_chain
+
+# load document
+loader = PyPDFLoader("/content/drive/MyDrive/HackGT/Dietary_Guidelines_for_Americans_2020-2025.pdf")
+documents = loader.load()
+# split the documents into chunks
+text_splitter = CharacterTextSplitter(chunk_size=10000, chunk_overlap=0)
+texts = text_splitter.split_documents(documents)
+# select which embeddings we want to use
+embeddings = OpenAIEmbeddings()
+# create the vectorestore to use as the index
+db = Chroma.from_documents(texts, embeddings)
+# expose this index in a retriever interface
+retriever = db.as_retriever(search_type="similarity", search_kwargs={"k":2})
+# create a chain to answer questions
+qa = RetrievalQA.from_chain_type(
+    llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=False)
+
+
+
 
 
 st_callback = StreamlitCallbackHandler(st.container())
 
 
 
-llm = OpenAI(temperature=0, streaming=True)
-tools = load_tools(["ddg-search"])
-agent = initialize_agent(
-    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
-)
+# llm = OpenAI(temperature=0, streaming=True)
+# tools = load_tools(["ddg-search"])
+# agent = initialize_agent(
+#     tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+# )
+
+text_input = st.text_input(
+        "Enter Date 👇",
+        label_visibility=st.session_state.visibility,
+        disabled=st.session_state.disabled,
+        placeholder=st.session_state.placeholder,
+    )
 
 if prompt := st.chat_input():
     st.chat_message("user").write(prompt)
     with st.chat_message("assistant"):
         st_callback = StreamlitCallbackHandler(st.container())
-        response = agent.run(prompt, callbacks=[st_callback])
-        st.write(response)
+
+        #Call query generator with text_input
+        result = qa({"query": query})
+
+        
+        
+        st.write(result['result'])