added persnolized way using github and leetcode

app.py

@@ -5,54 +5,172 @@ from crawl4ai.content_filter_strategy import PruningContentFilter
 from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
 from openai import AzureOpenAI
 from dotenv import load_dotenv
+
+# ---------------- ENV ----------------
 load_dotenv()
+
+def must_env(name):
+    v = os.getenv(name)
+    if not v:
+        raise RuntimeError(f"Missing env var: {name}")
+    return v
+
 client = AzureOpenAI(
-    api_key=os.getenv("AZURE_OPENAI_KEY").strip(),
+    api_key=must_env("AZURE_OPENAI_KEY"),
     api_version="2025-01-01-preview",
-    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT").strip()
+    azure_endpoint=must_env("AZURE_OPENAI_ENDPOINT"),
 )
 
-DEPLOYMENT_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT").strip()
-SERPER_API_KEY = os.getenv("SERPER_API_KEY").strip()
+DEPLOYMENT_NAME = must_env("AZURE_OPENAI_DEPLOYMENT")
+SERPER_API_KEY = must_env("SERPER_API_KEY")
+
+# =========================================================
+# =============== INTERVIEW INSIGHTS MODULE ==============
+# =========================================================
 
 def search_company_interviews(company):
-    headers = {"X-API-KEY": SERPER_API_KEY, "Content-Type": "application/json"}
-    query = f"{company} interview experience site:glassdoor.com OR site:geeksforgeeks.org OR site:prepinsta.com"
-    r = requests.post("https://google.serper.dev/search", headers=headers, json={"q": query})
+    headers = {
+        "X-API-KEY": SERPER_API_KEY,
+        "Content-Type": "application/json"
+    }
+    query = (
+        f"{company} interview experience "
+        "site:glassdoor.com OR site:geeksforgeeks.org OR site:prepinsta.com"
+    )
+    r = requests.post(
+        "https://google.serper.dev/search",
+        headers=headers,
+        json={"q": query, "num": 5},
+        timeout=15
+    )
+    r.raise_for_status()
     return [res["link"] for res in r.json().get("organic", [])[:3]]
 
 async def crawl_url(url):
     browser_conf = BrowserConfig(headless=True)
-    filter_strategy = PruningContentFilter()
+    filter_strategy = PruningContentFilter(threshold=0.48)  # Remove min_words parameter
     md_gen = DefaultMarkdownGenerator(content_filter=filter_strategy)
     run_conf = CrawlerRunConfig(markdown_generator=md_gen)
 
     async with AsyncWebCrawler(config=browser_conf) as crawler:
         result = await crawler.arun(url=url, config=run_conf)
-        return result.markdown.fit_markdown or result.markdown.raw_markdown
+        return (result.markdown.fit_markdown or "")[:2500]
 
 async def fetch_and_summarize(company):
     urls = search_company_interviews(company)
-    contents = []
-    for url in urls:
-        contents.append(await crawl_url(url))
-    context = "\n".join(contents)[:4000]
+    pages = await asyncio.gather(*[crawl_url(u) for u in urls])
+
+    context = "\n\n".join(pages)
+
     messages = [
-        {"role": "system", "content": "You summarize interview experiences for job seekers."},
-        {"role": "user", "content": f"Summarize interview process for {company} based on:\n{context}"}
+        {"role": "system", "content": "Summarize interview experiences concisely."},
+        {"role": "user", "content": f"""
+Summarize interview process for {company}:
+- Rounds
+- Difficulty
+- Topics asked
+- Preparation tips
+
+Content:
+{context}
+"""}
     ]
-    response = client.chat.completions.create(model=DEPLOYMENT_NAME, messages=messages, max_tokens=800)
-    return response.choices[0].message.content
 
-def get_interview_experience(company):
-    return asyncio.run(fetch_and_summarize(company))
+    response = client.chat.completions.create(
+        model=DEPLOYMENT_NAME,
+        messages=messages,
+        max_tokens=700
+    )
+
+    sources = "\n".join(f"- {u}" for u in urls)
+    return f"{response.choices[0].message.content}\n\n🔗 Sources:\n{sources}"
+
+# =========================================================
+# ========== ADAPTIVE LEARNING ECOSYSTEM MODULE ===========
+# =========================================================
+
+def fetch_github_stats(username):
+    url = f"https://github-readme-stats-fast.vercel.app/api/top-langs/?username={username}&layout=compact"
+    r = requests.get(url, timeout=10)
+    return r.text[:2000]  # SVG summary
+
+def fetch_leetcode_data(username):
+    base = f"https://leetcode-api-vercel.vercel.app/{username}"
+    endpoints = {
+        "profile": "",
+        "solved": "/solved",
+        "skill": "/skill",
+        "progress": "/progress",
+    }
+
+    data = {}
+    for k, path in endpoints.items():
+        r = requests.get(base + path, timeout=10)
+        if r.ok:
+            data[k] = r.json()
+    return data
+
+def generate_learning_plan(github_user, leetcode_user):
+    github_data = fetch_github_stats(github_user)
+    leetcode_data = fetch_leetcode_data(leetcode_user)
+
+    prompt = f"""
+You are an adaptive learning ecosystem focused on India's job market.
+
+GitHub language usage (SVG):
+{github_data}
+
+LeetCode performance (JSON):
+{leetcode_data}
+
+Tasks:
+1. Infer aptitude level
+2. Identify strong & weak skills
+3. Suggest 3 suitable job roles in India
+4. Create a 6-week adaptive learning roadmap
+5. Recommend LeetCode topics to focus next
+
+Be structured and practical.
+"""
+
+    resp = client.chat.completions.create(
+        model=DEPLOYMENT_NAME,
+        messages=[
+            {"role": "system", "content": "Design personalized learning paths. Make it practical. and use only the provided data. give correct output within 900 words or below"},
+            {"role": "user", "content": prompt},
+        ],
+        max_tokens=900,
+    )
+
+    return resp.choices[0].message.content
+
+# =========================================================
+# ======================= UI =============================
+# =========================================================
 
 with gr.Blocks() as demo:
-    gr.Markdown("## 💼 Interview Process and Expericence Finder")
-    company = gr.Textbox(label="Company Name")
-    output = gr.Textbox(label="Interview Insights", lines=15)
-    btn = gr.Button("Fetch")
-    btn.click(get_interview_experience, inputs=[company], outputs=[output])
+    gr.Markdown("# 🚀 AI Career Intelligence Platform")
+
+    with gr.Tabs():
+
+        # -------- TAB 1 --------
+        with gr.Tab("💼 Interview Insights"):
+            company = gr.Textbox(label="Company Name", placeholder="Amazon, Infosys")
+            interview_output = gr.Textbox(lines=18, label="Interview Summary")
+            btn1 = gr.Button("Fetch Interview Experience")
+            btn1.click(fetch_and_summarize, company, interview_output)
+
+        # -------- TAB 2 --------
+        with gr.Tab("🎓 Adaptive Learning Ecosystem"):
+            github_user = gr.Textbox(label="GitHub Username")
+            leetcode_user = gr.Textbox(label="LeetCode Username")
+            learning_output = gr.Textbox(lines=20, label="Personalized Learning Plan")
+            btn2 = gr.Button("Generate Learning Roadmap")
+            btn2.click(
+                generate_learning_plan,
+                inputs=[github_user, leetcode_user],
+                outputs=learning_output
+            )
 
 if __name__ == "__main__":
     demo.launch(share=False, server_name="0.0.0.0", server_port=7860, pwa=True)