Duplicate from mckplus/DocuChat

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+RUN python3 -m pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["panel", "serve", "/code/DocuChat.py", "--address", "0.0.0.0", "--port", "7860", "--allow-websocket-origin", "*"]
+
+RUN mkdir /.cache
+RUN chmod 777 /.cache
+RUN mkdir .chroma
+RUN chmod 777 .chroma

DocuChat.py

@@ -0,0 +1,87 @@
+import os
+import re
+import time
+import threading
+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
+
+# Set global sizing mode
+pn.config.sizing_mode = 'stretch_width'
+
+# Panel extension
+pn.extension('texteditor', template="bootstrap")
+
+file_input = pn.widgets.FileInput(height=45)
+openaikey = pn.widgets.PasswordInput(value="", placeholder="Enter your OpenAI API Key here...", height=45)
+prompt = pn.widgets.TextEditor(value="", placeholder="Ask a question...", height=100, toolbar=False)
+run_button = pn.widgets.Button(name="→", width=30, height=30)
+
+text_editor_with_button = pn.Row(prompt, run_button, align='end')
+
+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 toggle_run_button(state):
+    run_button.disabled = state
+
+def run_button_reappear():
+    time.sleep(10)
+    toggle_run_button(False)
+
+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']
+
+convos = []
+
+def qa_result(_):
+    toggle_run_button(True)
+    threading.Thread(target=run_button_reappear).start()  # Start a timer to re-enable the button
+
+    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(prompt.value)
+        prompt.value = ""  # Clear the prompt textbox
+        if prompt_text:
+            result = qa(file="/.cache/temp.pdf", query=prompt_text)
+            convos.extend([
+                pn.Row(pn.panel("👤", width=5), prompt_text),
+                pn.Row(pn.panel("🚀", width=5), pn.panel(result, style={'color': '#5b5b5b'}), height_policy='min', min_height=300)  # Adjusted height policy here
+            ])
+    toggle_run_button(False)
+    return pn.Column(*convos, sizing_mode='stretch_both', margin=10, min_height=300)
+    
+    
+qa_interactive = pn.panel(pn.bind(qa_result, run_button), loading_indicator=False) 
+
+output = pn.WidgetBox('', qa_interactive, scroll=True)
+
+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 [McKenzie](https://www.mckenzielloydsmith.com/home?utm_source=HuggingFace&utm_medium=PDF+Analyzer).
+    """),
+    pn.Row(file_input, openaikey), output, text_editor_with_button
+).servable()

README.md

@@ -0,0 +1,41 @@
+---
+title: DocuChat
+emoji: 📖
+colorFrom: green
+colorTo: pink
+sdk: docker
+pinned: true
+duplicated_from: mckplus/DocuChat
+---
+
+# DocuChat: The LangChain-Powered PDF Analysis 🚀
+
+Here's how it works:
+
+1. Upload a PDF: Select any PDF you want to analyze.
+2. Enter Your OpenAI API Key: To leverage OpenAI's powerful language models, you'll need to provide your API key.
+3. Ask a Question: Type your question into the text box and hit "Run."
+4. Get the Answer: The system will analyze your PDF and respond with the most relevant answer.
+
+
+# Technical Overview
+1. PDF Loading and Parsing
+- PDF Loader: Utilizes the PyPDFLoader from LangChain to read the uploaded PDF file.
+- Document Splitter: The CharacterTextSplitter divides the PDF into manageable chunks for further processing.
+2. Embeddings and Vector Storage
+- Embeddings: The OpenAIEmbeddings class is used to transform the text into a format that can be understood by the models.
+- Vector Storage: Chroma is used to store the vectors of the documents for quick retrieval.
+3. Question Answering
+- RetrievalQA: This class, from LangChain's chains, handles the core of the question-answering process.
+- OpenAI as Language Model: The OpenAI class is utilized as the core language model for the retrieval.
+4. Interactive UI
+- Panel Library: The entire interface is built using the Panel library, making it highly interactive and user-friendly.
+- Responsive Design: The UI adapts to various screen sizes, providing a smooth experience across devices.
+
+
+# Built by McKenzie
+This project is created and maintained by [McKenzie](https://www.mckenzielloydsmith.com/home?utm_source=HuggingFace&utm_medium=PDF+Analyzer). Contributions and feedback are always welcome!
+& credit to sophiamyang for the inspo & intro to panel 🙏
+
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+openai
+chromadb
+pypdf
+tiktoken
+panel>=0.12.0
+notebook