dual tabs again

app.py

@@ -2,6 +2,13 @@ import os
 
 import streamlit as st
 
+from langchain.chains import RetrievalQA
+from langchain.document_loaders import PyPDFLoader
+
+from langchain.vectorstores import Chroma
+from langchain.document_loaders import TextLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+
 st.set_page_config(page_title="CoreMind AI", layout="wide")
 
 st.header("CoreMind AI")
@@ -94,7 +101,6 @@ from langchain.llms import OpenAI
 # embeddings = OpenAIEmbeddings()
 # docsearch = Chroma(persist_directory="data", embedding_function=embeddings)
 
-from langchain.chains import RetrievalQA
 
 # qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=docsearch.as_retriever())
 
@@ -102,31 +108,59 @@ from langchain.chains import RetrievalQA
 
 # st.markdown("----")
 
-from langchain.document_loaders import PyPDFLoader
+
 
 if openai_key:
-    llm = OpenAI(temperature=0.9)
+    def question_answer(user_text, qa_temperature):
+        qa = RetrievalQA.from_chain_type(
+            llm=OpenAI(temperature=qa_temperature, model_name="gpt-3.5-turbo"), 
+            retriever=docsearch.as_retriever()
+        )
+        response = qa.run(user_text)
+        return response
+    
+    
+    loader = TextLoader("raw_data.txt")
+    embeddings = OpenAIEmbeddings()
+    docsearch = Chroma(persist_directory="data", embedding_function=embeddings)
+
+    qa_tab, understanding_tab = st.tabs(["Database Understanding", "PDF Understanding"])
+
+    with qa_tab:
+        st.header("Question Answering")
+        st.write("Dataset is Berkshire Hathaway's end of year reports for 1995, 1996 and 1997.")
+
+        qa_query = st.text_area("Enter your query", key="qa_query", help="Got a question you think your docs can answer? Just ask!")
+        
+        if qa_query:
+            response = question_answer(qa_query, 0.9)            
+            st.write(response)
+
+
+
+    with understanding_tab:
+        llm = OpenAI(temperature=0.9)
 
-    pdf_file = st.file_uploader("Upload a PDF", type=["pdf"], key="pdf_file")
-    if pdf_file:
-        with open("tmp_file.pdf", "wb") as f:
-            f.write(pdf_file.getbuffer())
+        pdf_file = st.file_uploader("Upload a PDF", type=["pdf"], key="pdf_file")
+        if pdf_file:
+            with open("tmp_file.pdf", "wb") as f:
+                f.write(pdf_file.getbuffer())
 
-        loader = PyPDFLoader("tmp_file.pdf")
-        pages = loader.load_and_split()
+            loader = PyPDFLoader("tmp_file.pdf")
+            pages = loader.load_and_split()
 
-        from langchain.vectorstores import FAISS
-        from langchain.embeddings.openai import OpenAIEmbeddings
+            from langchain.vectorstores import FAISS
+            from langchain.embeddings.openai import OpenAIEmbeddings
 
-        faiss_index = FAISS.from_documents(pages, OpenAIEmbeddings())
-        # docs = faiss_index.similarity_search("How will the community be engaged?", k=2)
-        # for doc in docs:
-        #     st.write(str(doc.metadata["page"]) + ":", doc.page_content[:300])
+            faiss_index = FAISS.from_documents(pages, OpenAIEmbeddings())
+            # docs = faiss_index.similarity_search("How will the community be engaged?", k=2)
+            # for doc in docs:
+            #     st.write(str(doc.metadata["page"]) + ":", doc.page_content[:300])
 
-        qa_prompt = st.text_area("Query your pdf", key="qa_prompt")
-        # qa_button = st.button("Let's go!", disabled=not (openai_key and qa_prompt), key="qa_button", help="Make sure you have entered your OpenAI API key and a query.")
+            qa_prompt = st.text_area("Query your pdf", key="qa_prompt")
+            # qa_button = st.button("Let's go!", disabled=not (openai_key and qa_prompt), key="qa_button", help="Make sure you have entered your OpenAI API key and a query.")
 
-        if qa_prompt:
+            if qa_prompt:
 
-            qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=faiss_index.as_retriever())
-            st.write(qa(qa_prompt))
+                qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=faiss_index.as_retriever())
+                st.write(qa(qa_prompt))

tmp_file.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52138f7464c477b10bf5068b8a211f059f8b90ba6b9c4d16c8ee434193a70be4
+size 1638808