Duplicate from lekkalar/chatgpt-for-pdfs

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,13 @@
+---
+title: ChatGPT For PDFs
+emoji: 👁
+colorFrom: indigo
+colorTo: gray
+sdk: gradio
+sdk_version: 3.33.1
+app_file: app.py
+pinned: false
+duplicated_from: lekkalar/chatgpt-for-pdfs
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import os
+import time
+
+
+from langchain.document_loaders import OnlinePDFLoader #for laoding the pdf
+from langchain.embeddings import OpenAIEmbeddings # for creating embeddings
+from langchain.vectorstores import Chroma # for the vectorization part
+from langchain.chains import ConversationalRetrievalChain # for conversing with chatGPT
+from langchain.chat_models import ChatOpenAI # the LLM model we'll use (ChatGPT)
+
+def loading_pdf():
+    return "Loading..."
+
+def pdf_changes(pdf_doc, open_ai_key):
+    if openai_key is not None:
+        os.environ['OPENAI_API_KEY'] = open_ai_key
+        #Load the pdf file
+        loader = OnlinePDFLoader(pdf_doc.name)
+        pages = loader.load_and_split()
+        
+        #Create an instance of OpenAIEmbeddings, which is responsible for generating embeddings for text
+        embeddings = OpenAIEmbeddings()
+
+        #To create a vector store, we use the Chroma class, which takes the documents (pages in our case), the embeddings instance, and a directory to store the vector data
+        vectordb = Chroma.from_documents(pages, embedding=embeddings)
+        
+        #Finally, we create the bot using the ConversationalRetrievalChain class
+        #A ConversationalRetrievalChain is similar to a RetrievalQAChain, except that the ConversationalRetrievalChain allows for 
+        #passing in of a chat history which can be used to allow for follow up questions.
+        global pdf_qa
+        pdf_qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0, model_name="gpt-4"), vectordb.as_retriever(), return_source_documents=False)
+        
+        return "Ready"
+    else:
+        return "Please provide an OpenAI API key"
+
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, ""
+
+def bot(history):
+    response = infer(history[-1][0], history)
+    history[-1][1] = ""
+    
+    for character in response:     
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
+    
+
+def infer(question, history):
+    
+    results = []
+    for human, ai in history[:-1]:
+        pair = (human, ai)
+        results.append(pair)
+    
+    chat_history = results
+    print(chat_history)
+    query = question
+    result = pdf_qa({"question": query, "chat_history": chat_history})
+    print(result)
+    return result["answer"]
+
+css="""
+#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+"""
+
+title = """
+<div style="text-align: center;max-width: 700px;">
+    <h1>Chatbot for PDFs - GPT-4</h1>
+    <p style="text-align: center;">Upload a .PDF, click the "Load PDF to LangChain" button, <br />
+    Wait for the Status to show Ready, start typing your questions. <br />
+    The app is set to store chat-history and is built on GPT-4</p>
+</div>
+"""
+
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        
+        with gr.Column():
+            openai_key = gr.Textbox(label="Your OpenAI API key", type="password")
+            pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="file")
+            with gr.Row():
+                langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
+                load_pdf = gr.Button("Load PDF to LangChain")
+        
+        chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+        question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+        submit_btn = gr.Button("Send Message")
+    load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
+    load_pdf.click(pdf_changes, inputs=[pdf_doc, openai_key], outputs=[langchain_status], queue=False)
+    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot
+    )
+    submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+openai
+tiktoken
+chromadb
+langchain
+unstructured
+unstructured[local-inference]