Create app.py

app.py

@@ -0,0 +1,80 @@
+import os
+import gradio as gr
+import fitz  # PyMuPDF for PDFs
+import docx
+import request
+HF_TOKEN = os.getenv("HF_TOKEN")
+# Load embedding model (fast & free)
+API_URL = "https://router.huggingface.co/hf-inference/models/sentence-transformers/all-MiniLM-L6-v2/pipeline/sentence-similarity"
+headers = {
+    "Authorization": f"Bearer {os.environ['HF_TOKEN']}",
+}
+
+
+
+# ---- Text extraction ----
+def extract_text(file):
+    if file.name.endswith(".pdf"):
+        text = ""
+        with fitz.open(stream=file.read(), filetype="pdf") as doc:
+            for page in doc:
+                text += page.get_text("text") + "\n"
+        return text
+    elif file.name.endswith(".docx"):
+        docf = docx.Document(file)
+        return "\n".join(p.text for p in docf.paragraphs)
+    return ""
+
+
+# ---- API embedding helper ----
+def get_embedding(text):
+    payload = {"inputs": text}
+    resp = requests.post(HF_API_URL, headers=HEADERS, json=payload, timeout=60)
+    data = resp.json()
+    if isinstance(data, list) and "embedding" in data[0]:
+        return np.array(data[0]["embedding"])
+    elif isinstance(data, list) and isinstance(data[0], list):
+        return np.array(data[0])
+    return np.zeros(384)
+
+
+# ---- CV ranking ----
+def rank_cvs(job_description, files):
+    if not job_description or not files:
+        return "⚠️ Please upload CVs and provide a job description."
+
+    job_emb = get_embedding(job_description)
+    scores, names = [], []
+
+    for f in files:
+        text = extract_text(f)
+        if not text.strip():
+            continue
+        cv_emb = get_embedding(text[:4000])  # limit text length
+        sim = np.dot(job_emb, cv_emb) / (
+            np.linalg.norm(job_emb) * np.linalg.norm(cv_emb)
+        )
+        scores.append(sim)
+        names.append(f.name)
+
+    top = sorted(zip(names, scores), key=lambda x: x[1], reverse=True)[:10]
+    return "\n\n".join(
+        [f"**{i+1}. {n}** — Similarity: `{s:.3f}`" for i, (n, s) in enumerate(top)]
+    )
+
+
+# ---- Gradio UI ----
+demo = gr.Interface(
+    fn=rank_cvs,
+    inputs=[
+        gr.Textbox(label="💼 Job Description", lines=5),
+        gr.File(label="📁 Upload CVs (PDF/DOCX)", file_count="multiple", type="file"),
+    ],
+    outputs=gr.Markdown(),
+    title="📄 AI CV Ranker (API-powered)",
+    description="Ranks uploaded CVs based on job relevance using Hugging Face API.",
+)
+
+if __name__ == "__main__":
+    demo.launch()
+