Update app.py

app.py

@@ -1,64 +1,64 @@
+import json
+from transformers import pipeline
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-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")
+# Load question-generation and question-answering pipelines
+qg_pipeline = pipeline("e2e-qg", model="valhalla/t5-small-qa-qg-hl")
+qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
 
+# Simple chunking: split on paragraphs (for demo)
+def split_chunks(text, max_len=200):
+    paragraphs = [p.strip() for p in text.split("\n") if p.strip()]
+    chunks = []
+    for p in paragraphs:
+        # further split long paragraphs
+        words = p.split()
+        if len(words) <= max_len:
+            chunks.append(p)
+        else:
+            for i in range(0, len(words), max_len):
+                chunk = " ".join(words[i : i + max_len])
+                chunks.append(chunk)
+    return chunks
 
-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)",
-        ),
-    ],
-)
+# Conversion function
+def convert_text(raw_text):
+    chunks = split_chunks(raw_text)
+    qna_list = []
+    for chunk in chunks:
+        # Generate raw Q&A pairs
+        try:
+            candidates = qg_pipeline(chunk)
+        except Exception:
+            continue
+        for cand in candidates:
+            question = cand.get("question") or cand.get("Q")
+            if not question:
+                continue
+            # Refine answer using QA pipeline
+            ans = qa_pipeline({"question": question, "context": chunk})
+            answer = ans.get("answer", "").strip()
+            # Append result
+            qna_list.append({"question": question.strip(), "answer": answer})
+    # Deduplicate
+    unique = []
+    seen = set()
+    for qa in qna_list:
+        key = (qa['question'], qa['answer'])
+        if key not in seen:
+            unique.append(qa)
+            seen.add(key)
+    return json.dumps(unique, indent=2, ensure_ascii=False)
 
+# Gradio interface
+def main():
+    with gr.Blocks() as demo:
+        gr.Markdown("# Handbook Text to Q&A Converter")
+        input_text = gr.Textbox(lines=10, placeholder="Paste handbook text here...", label="Raw Text")
+        output_json = gr.Textbox(lines=10, label="Generated Q&A JSON")
+        convert_btn = gr.Button("Convert")
+        convert_btn.click(fn=convert_text, inputs=input_text, outputs=output_json)
+    demo.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    main()