Add PDF RAG system

app.py

@@ -1,11 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+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
-"""
+# 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 extract_text_from_pdf(pdf_path):
+    doc = fitz.open(pdf_path)
+    text = ""
+    for page in doc:
+        text += page.get_text()
+    return text
 
 def respond(
     message,
@@ -14,7 +19,13 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    pdf_file
 ):
+    # Extract text from the uploaded PDF
+    if pdf_file:
+        pdf_text = extract_text_from_pdf(pdf_file.name)
+        system_message += f"\n\nContext from PDF:\n{pdf_text}"
+
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -39,9 +50,7 @@ def respond(
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -55,9 +64,9 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.File(label="Upload PDF")
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.22.2
+transformers
+gradio
+huggingface_hub
+pymupdf