Spaces:
Sleeping
Sleeping
| import os | |
| import re | |
| from langchain.chains import RetrievalQA | |
| from langchain.llms import OpenAI as LangchainOpenAI | |
| 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 | |
| # Include Lato font | |
| lato_font_link = "<link href='https://fonts.googleapis.com/css2?family=Lato:wght@400;700&display=swap' rel='stylesheet'>" | |
| pn.config.raw_css.append(lato_font_link) | |
| # Custom CSS to use Lato font | |
| pn.config.raw_css.append(""" | |
| .bk, .bk-root, .bk-widget { | |
| font-family: 'Lato', sans-serif !important; | |
| } | |
| .mckenzie-link a { | |
| font-weight: bold; | |
| color: #1b9aaa; | |
| } | |
| """) | |
| # Set global sizing mode | |
| pn.config.sizing_mode = 'stretch_width' | |
| # Panel extension | |
| pn.extension() | |
| class LangchainConversation: | |
| def __init__(self): | |
| self.file_input = pn.widgets.FileInput(height=45) | |
| self.openaikey = pn.widgets.PasswordInput(value="", placeholder="Enter your OpenAI API Key here...", height=45) | |
| self.chatbox = pn.widgets.ChatBox(height=300, primary_name="User") | |
| self.chatbox.param.watch(self._chat, 'value') | |
| self.chat_history = [] # Chat history to store previous queries and responses | |
| def _chat(self, event): | |
| user_message = event.new[-1] | |
| input = user_message.get("User") | |
| if input is None: | |
| return | |
| os.environ["OPENAI_API_KEY"] = self.openaikey.value | |
| if self.file_input.value is not None: | |
| self.file_input.save("/.cache/temp.pdf") | |
| prompt_text = self.remove_empty_lines(input) | |
| if prompt_text: | |
| result = self.qa(file="/.cache/temp.pdf", query=prompt_text) | |
| self.chatbox.append({"AI": result}) | |
| 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(self, file, query): | |
| # Consider chat history when processing new queries | |
| chat_history_str = "\\n".join([f"User: {q}\\nAI: {a}" for q, a in self.chat_history]) | |
| # Load, split, and analyze the document using the default text splitter | |
| loader = PyPDFLoader(file) | |
| documents = loader.load() | |
| text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0) # Default text splitting | |
| 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=LangchainOpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True) | |
| result = qa({"query": query + "\\n" + chat_history_str}) | |
| # Update chat history | |
| self.chat_history.append((query, result['result'])) | |
| return result['result'] | |
| def view(self): | |
| layout = pn.Column( | |
| pn.pane.Markdown(""" | |
| # DocuChat | |
| AI-Powered Query Engine for Document Insights (powered by LangChain & OpenAI) | |
| ## How it works: | |
| 1) Upload a PDF | |
| 2) Enter your OpenAI API key (get one via [OpenAI](https://platform.openai.com/account)) | |
| 3) Type a question and your document will get analyzed for an answer | |
| Built by <span class="mckenzie-link">[McKenzie](https://www.mckenzielloydsmith.com/home?utm_source=HuggingFace&utm_medium=PDF+Analyzer)</span>. | |
| """), | |
| pn.Row(self.file_input, self.openaikey), self.chatbox | |
| ).servable() | |
| return layout | |
| langchain_conversation = LangchainConversation() | |
| langchain_conversation.view() |