Linkedin connect

app.py

@@ -1,64 +1,96 @@
 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")
-
-
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+import os
+from urllib.parse import urlencode, parse_qs
+from http.server import BaseHTTPRequestHandler, HTTPServer
+import threading
+
+# Your LinkedIn App credentials
+CLIENT_ID = os.getenv("LINKEDIN_CLIENT_ID")
+CLIENT_SECRET = os.getenv("LINKEDIN_CLIENT_SECRET")
+REDIRECT_URI = "http://localhost:8080/callback"
+AUTH_URL = "https://www.linkedin.com/oauth/v2/authorization"
+TOKEN_URL = "https://www.linkedin.com/oauth/v2/accessToken"
+PROFILE_API = "https://api.linkedin.com/v2/me"
+EMAIL_API = "https://api.linkedin.com/v2/emailAddress?q=members&projection=(elements*(handle~))"
+
+access_token = None
+
+# Local web server to handle redirect URI callback
+class OAuthCallbackHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        global access_token
+        query = parse_qs(self.path.split('?', 1)[-1])
+        code = query.get('code')[0]
+
+        # Exchange code for token
+        token_data = {
+            'grant_type': 'authorization_code',
+            'code': code,
+            'redirect_uri': REDIRECT_URI,
+            'client_id': CLIENT_ID,
+            'client_secret': CLIENT_SECRET
+        }
+
+        response = requests.post(TOKEN_URL, data=token_data)
+        token_json = response.json()
+        access_token = token_json.get('access_token')
+
+        self.send_response(200)
+        self.end_headers()
+        self.wfile.write(b'Authentication successful. Return to the app.')
+
+# Run server in background
+def start_oauth_server():
+    server = HTTPServer(('localhost', 8080), OAuthCallbackHandler)
+    server.handle_request()
+
+def get_authorization_url():
+    params = {
+        'response_type': 'code',
+        'client_id': CLIENT_ID,
+        'redirect_uri': REDIRECT_URI,
+        'scope': 'r_liteprofile r_emailaddress'
+    }
+    return f"{AUTH_URL}?{urlencode(params)}"
+
+# Hugging Face summarization
+def summarize_profile(name, headline, email):
+    text = f"{name} is a professional with expertise in: {headline}. Contact: {email}"
+    response = requests.post(
+        "https://api-inference.huggingface.co/models/facebook/bart-large-cnn",
+        headers={"Authorization": f"Bearer {os.getenv('HF_API_KEY')}"},
+        json={"inputs": text}
+    )
+    return response.json()[0]["summary_text"]
+
+def linkedIn_summary_flow():
+    global access_token
+    # Trigger OAuth
+    threading.Thread(target=start_oauth_server).start()
+    return f"[Click here to authorize LinkedIn]({get_authorization_url()})"
+
+def fetch_and_summarize(_):
+    headers = {"Authorization": f"Bearer {access_token}"}
+    profile = requests.get(PROFILE_API, headers=headers).json()
+    email_data = requests.get(EMAIL_API, headers=headers).json()
+
+    name = profile.get("localizedFirstName", "") + " " + profile.get("localizedLastName", "")
+    headline = profile.get("localizedHeadline", "")
+    email = email_data['elements'][0]['handle~']['emailAddress']
+
+    summary = summarize_profile(name, headline, email)
+    return f"**Name:** {name}\n**Headline:** {headline}\n**Email:** {email}\n\n**Summary:** {summary}"
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🔗 LinkedIn Profile Summarizer")
+    gr.Markdown("1. Click to authorize via LinkedIn\n2. Fetch & summarize your profile")
+
+    btn_auth = gr.Button("🔐 Connect to LinkedIn")
+    btn_fetch = gr.Button("📄 Summarize My Profile")
+    output = gr.Textbox(label="Summary", lines=10)
+
+    btn_auth.click(linkedIn_summary_flow, outputs=output)
+    btn_fetch.click(fetch_and_summarize, inputs=[], outputs=output)
+
+demo.launch()