Upload GPT-4_PDF_summary.py

GPT-4_PDF_summary.py

@@ -1,16 +1,11 @@
 #!/usr/bin/env python
 # coding: utf-8
 
+# !pip install langchain openai chromadb tiktoken pypdf panel
 # In[ ]:
 
 
-get_ipython().system('pip install langchain openai chromadb tiktoken pypdf panel')
-
-
-# In[ ]:
-
-
-import os 
+import os
 from langchain.chains import RetrievalQA
 from langchain.llms import OpenAI
 from langchain.document_loaders import TextLoader
@@ -50,7 +45,7 @@ select_k = pn.widgets.IntSlider(
     name="Number of relevant chunks", start=1, end=5, step=1, value=2
 )
 select_chain_type = pn.widgets.RadioButtonGroup(
-    name='Chain type', 
+    name='Chain type',
     options=['stuff', 'map_reduce', "refine", "map_rerank"]
 )
 
@@ -79,8 +74,9 @@ def qa(file, query, chain_type, k):
     # 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": k})
-    # create a chain to answer questions 
+    retriever = db.as_retriever(
+        search_type="similarity", search_kwargs={"k": k})
+    # create a chain to answer questions
     qa = RetrievalQA.from_chain_type(
         llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)
     result = qa({"query": query})
@@ -93,16 +89,18 @@ def qa(file, query, chain_type, k):
 
 convos = []  # store all panel objects in a list
 
+
 def qa_result(_):
     os.environ["OPENAI_API_KEY"] = openaikey.value
-    
-    # save pdf file to a temp file 
+
+    # save pdf file to a temp file
     if file_input.value is not None:
         file_input.save("/.cache/temp.pdf")
-    
+
         prompt_text = prompt.value
         if prompt_text:
-            result = qa(file="/.cache/temp.pdf", query=prompt_text, chain_type=select_chain_type.value, k=select_k.value)
+            result = qa(file="/.cache/temp.pdf", query=prompt_text,
+                        chain_type=select_chain_type.value, k=select_k.value)
             convos.extend([
                 pn.Row(
                     pn.panel("\U0001F60A", width=10),
@@ -114,11 +112,12 @@ def qa_result(_):
                     pn.Column(
                         result["result"],
                         "Relevant source text:",
-                        pn.pane.Markdown('\n--------------------------------------------------------------------\n'.join(doc.page_content for doc in result["source_documents"]))
+                        pn.pane.Markdown('\n--------------------------------------------------------------------\n'.join(
+                            doc.page_content for doc in result["source_documents"]))
                     )
                 )
             ])
-            #return convos
+            # return convos
     return pn.Column(*convos, margin=15, width=575, min_height=400)
 
 
@@ -134,7 +133,8 @@ qa_interactive = pn.panel(
 # In[8]:
 
 
-output = pn.WidgetBox('*Output will show up here:*', qa_interactive, width=630, scroll=True)
+output = pn.WidgetBox('*Output will show up here:*',
+                      qa_interactive, width=630, scroll=True)
 
 
 # In[9]:
@@ -148,9 +148,8 @@ pn.Column(
     1) Upload a PDF. 2) Enter OpenAI API key. This costs $. Set up billing at [OpenAI](https://platform.openai.com/account). 3) Type a question and click "Run".
     
     """),
-    pn.Row(file_input,openaikey),
+    pn.Row(file_input, openaikey),
     output,
     widgets
 
 ).servable()
-