Update app.py

app.py

@@ -1,63 +1,77 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModel
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
+import fitz  # PyMuPDF
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# Function to get available models from Hugging Face
+def get_hf_models():
+    return ["Qwen/Qwen2.5-3B-Instruct", "HuggingFaceH4/zephyr-7b-beta", "mistralai/Mistral-7B-Instruct-v0.1"]
+
+# Function to extract text from a PDF
+def extract_text_from_pdf(pdf_path):
+    text = ""
+    with fitz.open(pdf_path) as doc:
+        for page in doc:
+            text += page.get_text()
+    return text
+
+# Function for manual RAG
+def manual_rag(query, context, client):
+    prompt = f"Context: {context}\n\nQuestion: {query}\n\nAnswer:"
+    response = client.text_generation(prompt, max_new_tokens=512)
+    return response
+
+# Function for classic RAG
+def classic_rag(query, pdf_path, client, embedder):
+    text = extract_text_from_pdf(pdf_path)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    chunks = text_splitter.split_text(text)
+    embeddings = HuggingFaceEmbeddings(model_name=embedder)
+    db = FAISS.from_texts(chunks, embeddings)
+    docs = db.similarity_search(query, k=3)
+    context = " ".join([doc.page_content for doc in docs])
+    response = manual_rag(query, context, client)
+    return response, context
+
+# Function for response without RAG
+def no_rag(query, client):
+    response = client.text_generation(query, max_new_tokens=512)
+    return response
+
+# Gradio interface function
+def process_query(query, pdf_path, llm_choice, embedder_choice):
+    client = InferenceClient(llm_choice)
+    full_text = extract_text_from_pdf(pdf_path)
+    no_rag_response = no_rag(query, client)
+    manual_rag_response = manual_rag(query, full_text, client)
+    classic_rag_response, classic_rag_context = classic_rag(query, pdf_path, client, embedder_choice)
+    return no_rag_response, manual_rag_response, classic_rag_response, full_text, classic_rag_context
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_query,
+    inputs=[
+        gr.Textbox(label="Votre question"),
+        gr.File(label="Chargez votre PDF"),
+        gr.Dropdown(choices=get_hf_models(), label="Choisissez le LLM", value="Qwen/Qwen2.5-3B-Instruct"),
+        gr.Dropdown(choices=["sentence-transformers/all-MiniLM-L6-v2", "nomic-ai/nomic-embed-text-v1.5"],
+                    label="Choisissez l'Embedder", value="sentence-transformers/all-MiniLM-L6-v2")
     ],
+    outputs=[
+        gr.Textbox(label="Réponse sans RAG"),
+        gr.Textbox(label="Réponse avec RAG manuel"),
+        gr.Textbox(label="Réponse avec RAG classique"),
+        gr.Textbox(label="Texte complet du PDF (pour RAG manuel)", lines=10),
+        gr.Textbox(label="Contexte extrait (pour RAG classique)", lines=10)
+    ],
+    title="Tutoriel RAG - Comparaison des méthodes",
+    description="Posez une question sur le contenu d'un PDF et comparez les réponses obtenues avec différentes méthodes de RAG.",
+    theme="default"
 )
 
-
+# Launch the application
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()