Create DocuChat.py

DocuChat.py

@@ -0,0 +1,61 @@
+import os
+import re
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+import panel as pn
+pn.extension()
+
+# Set global sizing mode
+pn.config.sizing_mode = 'stretch_width'
+
+# Panel extension
+pn.extension('chatbox', template="bootstrap")
+
+file_input = pn.widgets.FileInput(height=45)
+openaikey = pn.widgets.PasswordInput(value="", placeholder="Enter your OpenAI API Key here...", height=45)
+ChatBox = pn.widgets.ChatBox(height=300, primary_name="User", allow_input=True)
+
+def remove_empty_lines(text):
+    lines = re.split(r'\r\n|\r|\n', text)
+    return '\n'.join([line.strip() for line in lines if line.strip()])
+
+def qa(file, query):
+    loader = PyPDFLoader(file)
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    texts = text_splitter.split_documents(documents)
+    embeddings = OpenAIEmbeddings()
+    db = Chroma.from_documents(texts, embeddings)
+    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 3})
+    qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True)
+    result = qa({"query": query})
+    return result['result']
+
+def qa_result(event):
+    # Check if the event was triggered by a new user input
+    if len(event.new) > len(event.old):
+        os.environ["OPENAI_API_KEY"] = openaikey.value
+        if file_input.value is not None:
+            file_input.save("/.cache/temp.pdf")
+            prompt_text = remove_empty_lines(event.new[-1][ChatBox.primary_name])
+            print("Prompt text:", prompt_text)  # Debugging print statement
+            if prompt_text:
+                result = qa(file="/.cache/temp.pdf", query=prompt_text)
+                print("Result:", result)  # Debugging print statement
+                # Append the AI's response to the chatbox
+                ChatBox.value.append({"AI": result})
+
+ChatBox.param.watch(qa_result, 'value')
+
+layout = pn.Column(
+    pn.pane.Markdown("""
+    # DocuChat
+    AI-Powered Query Engine for Document Insights (powered by LangChain & OpenAI)
+    ...
+    """),
+    pn.Row(file_input, openaikey), ChatBox
+).servable()