Upload 4 files

README (3).md

@@ -0,0 +1,12 @@
+---
+title: "Chat PDF"
+emoji: 📄
+colorFrom: purple
+colorTo: pink
+sdk: gradio
+sdk_version: 3.28.2
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app (1).py

@@ -0,0 +1,91 @@
+import gradio as gr
+import os
+import time
+from langchain.document_loaders import OnlinePDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import ConversationalRetrievalChain
+
+def loading_pdf():
+    return "加载中...⏳"
+
+def pdf_changes(pdf_doc, openai_api_key, chunk_size, chunk_overlap, temperature, return_source):
+    if not openai_api_key:
+        return "你忘记了OpenAI API密钥🗝️"
+    os.environ['OPENAI_API_KEY'] = openai_api_key
+    loader = OnlinePDFLoader(pdf_doc.name)
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
+    texts = text_splitter.split_documents(documents)
+    embeddings = OpenAIEmbeddings()
+    db = Chroma.from_documents(texts, embeddings)
+    retriever = db.as_retriever()
+    global qa 
+    qa = ConversationalRetrievalChain.from_llm(
+        llm=OpenAI(temperature=temperature,model="text-davinci-003",max_tokens=1000),
+        retriever=retriever, 
+        return_source_documents=return_source)
+    return "准备就绪🚀"
+
+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):
+    res = []
+    for human, ai in history[:-1]:
+        pair = (human, ai)
+        res.append(pair)
+    chat_history = res
+    query = question
+    result = qa({"question": query, "chat_history": chat_history})
+    return result["answer"]
+
+css="""
+#col-container {max-width: 700px; margin-left: auto; margin-right: auto; background-color: #f0f0f0;}
+"""
+
+title = """
+<div style="text-align: center;max-width: 700px;">
+    <h1 style="color: #3399FF; font-family: 'Courier New', Courier, monospace;">Chat PDF[text-davinci-003]📚</h1>
+    <p style="text-align: center;color: #666666; font-family: 'Courier New', Courier, monospace;">上传你的PDF，并将其加载到向量库中，<br />
+    当一切准备就绪，你就可以开始提出关于pdf的问题了 🧐 <br />
+    此版本使用text-davinci-003作为LLM</p>
+</div>
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        with gr.Column():
+            openai_api_key = gr.Textbox(label="你的OpenAI API密钥🔐", type="password")
+            pdf_doc = gr.File(label="加载一个pdf📄", file_types=['.pdf'], type="file")
+            with gr.Row():
+                langchain_status = gr.Textbox(label="状态📊", placeholder="", interactive=False)
+                chunk_size_slider = gr.Slider(minimum=100, maximum=2000, value=1000, step=100, label='块大小📏')
+                chunk_overlap_slider = gr.Slider(minimum=0, maximum=1000, value=0, step=50, label='块重叠🔀')
+                temperature_slider = gr.Slider(minimum=0.1, maximum=1.0, value=0.5, step=0.1, label='温度🌡️')
+                return_source_checkbox = gr.Checkbox(label='返回源文件📑', default=False)
+                load_pdf = gr.Button("加载PDF到LangChain🔄")
+        chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+        question = gr.Textbox(label="问题❓", placeholder="输入你的问题并按回车 ")
+        submit_btn = gr.Button("发送消息📨")
+    load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
+    load_pdf.click(pdf_changes, inputs=[pdf_doc, openai_api_key, chunk_size_slider, chunk_overlap_slider, temperature_slider, return_source_checkbox], 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()

gitattributes (2).txt

@@ -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

requirements (2).txt

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