Duplicate from fffiloni/langchain-chat-with-pdf

Co-authored-by: Sylvain Filoni <fffiloni@users.noreply.huggingface.co>

.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: Chat with PDF
+emoji: 📄🤖
+colorFrom: purple
+colorTo: pink
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+duplicated_from: fffiloni/langchain-chat-with-pdf
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+import gradio as gr
+
+from langchain.document_loaders import OnlinePDFLoader
+
+from langchain.text_splitter import CharacterTextSplitter
+text_splitter = CharacterTextSplitter(chunk_size=350, chunk_overlap=0)
+
+from langchain.llms import HuggingFaceHub
+flan_ul2 = HuggingFaceHub(repo_id="google/flan-ul2", model_kwargs={"temperature":0.1, "max_new_tokens":300})
+
+from langchain.embeddings import HuggingFaceHubEmbeddings
+embeddings = HuggingFaceHubEmbeddings()
+
+from langchain.vectorstores import Chroma
+
+from langchain.chains import RetrievalQA
+def loading_pdf():
+    return "Loading..."
+def pdf_changes(pdf_doc):
+    loader = OnlinePDFLoader(pdf_doc.name)
+    documents = loader.load()
+    texts = text_splitter.split_documents(documents)
+    db = Chroma.from_documents(texts, embeddings)
+    retriever = db.as_retriever()
+    global qa 
+    qa = RetrievalQA.from_chain_type(llm=flan_ul2, chain_type="stuff", retriever=retriever, return_source_documents=True)
+    return "Ready"
+
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, ""
+
+def bot(history):
+    response = infer(history[-1][0])
+    history[-1][1] = response['result']
+    return history
+
+def infer(question):
+    
+    query = question
+    result = qa({"query": query})
+
+    return result
+
+css="""
+#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+"""
+
+title = """
+<div style="text-align: center;max-width: 700px;">
+    <h1>Chat with PDF</h1>
+    <p style="text-align: center;">Upload a .PDF from your computer, click the "Load PDF to LangChain" button, <br />
+    when everything is ready, you can start asking questions about the pdf ;)</p>
+</div>
+"""
+
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(title)
+        
+        with gr.Column():
+            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)
+        with gr.Row():
+            question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+    load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
+    load_pdf.click(pdf_changes, pdf_doc, langchain_status, queue=False)
+    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+huggingface_hub
+chromadb
+langchain
+unstructured
+unstructured[local-inference]