Upload 2 files

app.py

@@ -0,0 +1,92 @@
+import os
+import io
+import math
+import requests
+import pdfplumber
+import gradio as gr
+
+HF_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
+EMBED_MODEL = "ibm-granite/granite-embedding-english-r2"
+GEN_MODEL = "ibm-granite/granite-3.3-2b-instruct"
+
+store = []  # simple in-memory vector store
+
+
+def hf_request(model, payload):
+    res = requests.post(
+        f"https://api-inference.huggingface.co/models/{model}",
+        headers={"Authorization": f"Bearer {HF_TOKEN}"},
+        json=payload,
+    )
+    res.raise_for_status()
+    return res.json()
+
+
+def cosine(a, b):
+    dot = sum(x * y for x, y in zip(a, b))
+    na = math.sqrt(sum(x * x for x in a))
+    nb = math.sqrt(sum(y * y for y in b))
+    return dot / (na * nb + 1e-9)
+
+
+def upload_pdf(pdf_file):
+    global store
+    if pdf_file is None:
+        return "Please upload a PDF first."
+
+    with open(pdf_file.name, "rb") as f:
+        pdf_bytes = f.read()
+
+    text = ""
+    with pdfplumber.open(io.BytesIO(pdf_bytes)) as pdf:
+        for page in pdf.pages:
+            text += page.extract_text() or ""
+
+    chunks, buf = [], ""
+    for sent in text.split(". "):
+        if len(buf) + len(sent) > 800:
+            chunks.append(buf.strip())
+            buf = sent
+        else:
+            buf += " " + sent
+    if buf:
+        chunks.append(buf.strip())
+
+    if not chunks:
+        return "No text extracted from PDF."
+
+    embeds = hf_request(EMBED_MODEL, {"inputs": chunks})
+    store = [{"text": c, "vec": embeds[i]} for i, c in enumerate(chunks)]
+
+    return f"✅ PDF processed. {len(store)} chunks indexed."
+
+
+def ask_question(q):
+    if not store:
+        return "⚠️ Please upload a PDF first."
+
+    q_embed = hf_request(EMBED_MODEL, {"inputs": [q]})[0]
+    best = max(store, key=lambda it: cosine(q_embed, it["vec"]))
+
+    prompt = f"Answer the question using this context:\n{best['text']}\n\nQ: {q}"
+    out = hf_request(GEN_MODEL, {"inputs": prompt})
+
+    return out[0].get("generated_text", "No answer")
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 📘 StudyMate — PDF Q&A with IBM Granite")
+    with gr.Row():
+        pdf_file = gr.File(label="Upload PDF", file_types=[".pdf"])
+        upload_btn = gr.Button("Process PDF")
+    status = gr.Textbox(label="Status", interactive=False)
+
+    with gr.Row():
+        question = gr.Textbox(label="Ask a Question")
+        ask_btn = gr.Button("Get Answer")
+    answer = gr.Textbox(label="Answer", interactive=False)
+
+    upload_btn.click(upload_pdf, inputs=pdf_file, outputs=status)
+    ask_btn.click(ask_question, inputs=question, outputs=answer)
+
+demo.launch()

requirements.txt

@@ -1,3 +1,3 @@
-altair
-pandas
-streamlit
+gradio
+pdfplumber
+requests