Create app.py

app.py

@@ -0,0 +1,497 @@
+import json
+import textwrap
+from typing import Dict, Any, List, Tuple, Optional
+
+import gradio as gr
+import requests
+import matplotlib.pyplot as plt
+from matplotlib.figure import Figure
+
+
+# ============================================================
+#  LLM CALLER (OPENAI-COMPATIBLE, GPT-4.1 BY DEFAULT)
+# ============================================================
+
+def call_chat_completion(
+    api_key: str,
+    base_url: str,
+    model: str,
+    system_prompt: str,
+    user_prompt: str,
+    max_completion_tokens: int = 1800,
+) -> str:
+    """
+    OpenAI-compatible /v1/chat/completions helper.
+
+    - Uses new-style `max_completion_tokens` (for GPT-4.1, GPT-4o, etc.)
+    - Falls back to legacy `max_tokens` if needed.
+    - Does NOT send temperature/top_p so it's safe with strict models.
+    """
+    if not api_key:
+        raise ValueError("LLM API key is required.")
+
+    if not base_url:
+        base_url = "https://api.openai.com"
+
+    url = base_url.rstrip("/") + "/v1/chat/completions"
+
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json",
+    }
+
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_prompt},
+        ],
+        "max_completion_tokens": max_completion_tokens,
+    }
+
+    resp = requests.post(url, headers=headers, json=payload, timeout=60)
+
+    # Fallback for providers that still expect `max_tokens`
+    if resp.status_code == 400 and "max_completion_tokens" in resp.text:
+        payload.pop("max_completion_tokens", None)
+        payload["max_tokens"] = max_completion_tokens
+        resp = requests.post(url, headers=headers, json=payload, timeout=60)
+
+    if resp.status_code != 200:
+        raise RuntimeError(
+            f"LLM API error {resp.status_code}: {resp.text[:500]}"
+        )
+
+    data = resp.json()
+    try:
+        return data["choices"][0]["message"]["content"]
+    except Exception as e:
+        raise RuntimeError(
+            f"Unexpected LLM response format: {e}\n\n{json.dumps(data, indent=2)}"
+        )
+
+
+# ============================================================
+#  FIRECRAWL SCRAPER (OPTIONAL)
+# ============================================================
+
+def call_firecrawl_scrape(
+    firecrawl_key: str,
+    url: str,
+    formats: Optional[List[str]] = None,
+) -> str:
+    """
+    Calls Firecrawl's /v0/scrape endpoint to get cleaned markdown/HTML
+    for a single URL.
+
+    Docs: https://docs.firecrawl.dev/api-reference/endpoint/scrape
+    """
+    if not firecrawl_key:
+        raise ValueError("Firecrawl API key is missing.")
+
+    if not url:
+        raise ValueError("URL is required to use Firecrawl.")
+
+    api_url = "https://api.firecrawl.dev/v0/scrape"
+    headers = {
+        "Authorization": f"Bearer {firecrawl_key}",
+        "Content-Type": "application/json",
+    }
+
+    payload: Dict[str, Any] = {"url": url}
+    if formats:
+        payload["formats"] = formats
+
+    resp = requests.post(api_url, headers=headers, json=payload, timeout=60)
+
+    if resp.status_code != 200:
+        raise RuntimeError(
+            f"Firecrawl error {resp.status_code}: {resp.text[:400]}"
+        )
+
+    data = resp.json()
+    # Default: try markdown first, fall back to raw HTML or text if structure differs
+    # Common shape: { "data": { "markdown": "..." } }
+    if isinstance(data, dict):
+        # Nested under "data"
+        inner = data.get("data", {})
+        if isinstance(inner, dict):
+            if "markdown" in inner and isinstance(inner["markdown"], str):
+                return inner["markdown"]
+            if "html" in inner and isinstance(inner["html"], str):
+                return inner["html"]
+        # If the service changes shape, last fallback: stringify
+    return json.dumps(data)
+
+
+# ============================================================
+#  ANALYSIS PROMPT + PARSING
+# ============================================================
+
+ANALYSIS_SYSTEM_PROMPT = """
+You are an expert strategy analyst.
+
+Given some web content (or pasted text) plus a short user description,
+you will produce a concise, executive-ready analysis in JSON.
+
+Return ONLY JSON using this schema:
+
+{
+  "executive_summary": "string",
+  "key_points": ["string", ...],
+  "opportunities": ["string", ...],
+  "risks": ["string", ...],
+  "recommended_actions": [
+    {
+      "title": "string",
+      "area": "string",
+      "description": "string"
+    }
+  ]
+}
+"""
+
+def build_analysis_user_prompt(
+    url: str,
+    content_preview: str,
+    user_notes: str,
+    focus: str,
+) -> str:
+    truncated = content_preview[:6000]  # keep context reasonable
+    return f"""
+Source URL: {url or "N/A"}
+
+Focus area: {focus}
+
+User notes / context:
+{user_notes or "N/A"}
+
+Scraped or pasted content (truncated if long):
+\"\"\"{truncated}\"\"\"
+""".strip()
+
+
+def parse_analysis_json(raw_text: str) -> Dict[str, Any]:
+    """Strip fences and extract JSON payload."""
+    txt = raw_text.strip()
+
+    if txt.startswith("```"):
+        parts = txt.split("```")
+        txt = next((p for p in parts if "{" in p and "}" in p), parts[-1])
+
+    first = txt.find("{")
+    last = txt.rfind("}")
+    if first == -1 or last == -1:
+        raise ValueError("No JSON detected in model output.")
+
+    return json.loads(txt[first:last + 1])
+
+
+def analysis_to_markdown(analysis: Dict[str, Any]) -> str:
+    """Render the JSON analysis as a short executive brief in Markdown."""
+
+    def bullet(items: List[str]) -> str:
+        if not items:
+            return "_None identified._"
+        return "\n".join(f"- {i}" for i in items)
+
+    md: List[str] = []
+
+    md.append("## Executive Summary")
+    md.append(analysis.get("executive_summary", "N/A"))
+
+    md.append("\n## Key Points")
+    md.append(bullet(analysis.get("key_points", [])))
+
+    md.append("\n## Opportunities")
+    md.append(bullet(analysis.get("opportunities", [])))
+
+    md.append("\n## Risks")
+    md.append(bullet(analysis.get("risks", [])))
+
+    md.append("\n## Recommended Actions")
+    actions = analysis.get("recommended_actions", [])
+    if not actions:
+        md.append("_None suggested yet — refine your prompt or focus._")
+    else:
+        for idx, act in enumerate(actions, start=1):
+            title = act.get("title", f"Action {idx}")
+            area = act.get("area", "General")
+            desc = act.get("description", "")
+            md.append(f"### {idx}. {title}")
+            md.append(f"**Area:** {area}")
+            md.append(desc or "_No description provided._")
+
+    return "\n\n".join(md)
+
+
+# ============================================================
+#  SIMPLE DATA VISUAL — COUNTS BY CATEGORY
+# ============================================================
+
+def analysis_to_figure(analysis: Dict[str, Any]) -> Figure:
+    """
+    Basic bar chart: how many items per category (points, opportunities, risks, actions).
+    Visualizes "density" of insights.
+    """
+    labels = ["Key Points", "Opportunities", "Risks", "Actions"]
+    values = [
+        len(analysis.get("key_points", []) or []),
+        len(analysis.get("opportunities", []) or []),
+        len(analysis.get("risks", []) or []),
+        len(analysis.get("recommended_actions", []) or []),
+    ]
+
+    fig, ax = plt.subplots(figsize=(5, 3))
+    ax.bar(labels, values)
+    ax.set_ylabel("Count")
+    ax.set_title("Insight Density by Category")
+    fig.tight_layout()
+    return fig
+
+
+# ============================================================
+#  SAMPLE PRESETS
+# ============================================================
+
+SAMPLE_CONFIGS: Dict[str, Dict[str, str]] = {
+    "AI / Tech Policy Article": {
+        "url": "https://www.whitehouse.gov/briefing-room/",
+        "notes": "Focus on AI policy, workforce impact, and org-readiness.",
+        "focus": "Policy / Regulation",
+    },
+    "Competitor Product Page": {
+        "url": "https://example.com/",
+        "notes": "Assume this is a competitor's SaaS pricing page.",
+        "focus": "Product / Market",
+    },
+    "Industry Research Report": {
+        "url": "https://example.org/report",
+        "notes": "Treat as a long-form industry trend report.",
+        "focus": "Industry / Strategy",
+    },
+}
+
+def load_sample(name: str) -> Tuple[str, str, str]:
+    if not name or name not in SAMPLE_CONFIGS:
+        return "", "", "General insight synthesis"
+    cfg = SAMPLE_CONFIGS[name]
+    return cfg["url"], cfg["notes"], cfg["focus"]
+
+
+# ============================================================
+#  MAIN HANDLER FOR GRADIO
+# ============================================================
+
+def generate_brief_ui(
+    llm_key_state: str,
+    llm_key_input: str,
+    base_url: str,
+    model_name: str,
+    firecrawl_key: str,
+    url: str,
+    pasted_text: str,
+    user_notes: str,
+    focus: str,
+):
+    """
+    Master UI handler:
+    - decides whether to call Firecrawl (if key + URL)
+    - merges scraped content with pasted text
+    - calls LLM and renders outputs
+    """
+    llm_key = llm_key_input or llm_key_state
+    if not llm_key:
+        return (
+            "⚠️ Please enter your LLM API key in the left panel.",
+            "",
+            analysis_to_figure({"key_points": [], "opportunities": [], "risks": [], "recommended_actions": []}),
+            llm_key_state,
+        )
+
+    if not url and not pasted_text:
+        return (
+            "⚠️ Provide at least a URL or some pasted text.",
+            "",
+            analysis_to_figure({"key_points": [], "opportunities": [], "risks": [], "recommended_actions": []}),
+            llm_key_state,
+        )
+
+    # 1. Scrape via Firecrawl if URL + key are set
+    scraped_content = ""
+    if url and firecrawl_key:
+        try:
+            scraped_content = call_firecrawl_scrape(firecrawl_key, url, formats=["markdown"])
+        except Exception as e:
+            scraped_content = f"(Firecrawl error: {e})"
+
+    # 2. Compose content preview (scraped + pasted)
+    content_preview_parts = []
+    if scraped_content:
+        content_preview_parts.append(scraped_content)
+    if pasted_text:
+        content_preview_parts.append("\n\nUser-pasted text:\n" + pasted_text)
+
+    content_preview = "\n\n".join(content_preview_parts)
+
+    # 3. Build prompt and call LLM
+    user_prompt = build_analysis_user_prompt(url, content_preview, user_notes, focus)
+    model = model_name or "gpt-4.1"
+
+    try:
+        raw = call_chat_completion(
+            api_key=llm_key,
+            base_url=base_url,
+            model=model,
+            system_prompt=ANALYSIS_SYSTEM_PROMPT,
+            user_prompt=user_prompt,
+            max_completion_tokens=1800,
+        )
+
+        analysis = parse_analysis_json(raw)
+        md = analysis_to_markdown(analysis)
+        fig = analysis_to_figure(analysis)
+        json_out = json.dumps(analysis, indent=2, ensure_ascii=False)
+
+        return md, json_out, fig, llm_key
+
+    except Exception as e:
+        empty_fig = analysis_to_figure({"key_points": [], "opportunities": [], "risks": [], "recommended_actions": []})
+        return f"❌ Error generating brief:\n\n{e}", "", empty_fig, llm_key_state
+
+
+# ============================================================
+#  GRADIO UI
+# ============================================================
+
+with gr.Blocks(title="ZEN Web Insight Brief Builder") as demo:
+    gr.Markdown(
+        """
+# 🌐 ZEN Web Insight Brief Builder
+
+Turn any URL (plus optional Firecrawl scrape) into a structured,
+actionable executive brief:
+
+1. **Configure API keys** (LLM + optional Firecrawl)  
+2. **Paste a URL and/or text**  
+3. **Get an executive summary, risks, opportunities, and actions**
+"""
+    )
+
+    llm_key_state = gr.State("")
+
+    with gr.Row():
+        # LEFT: API + samples
+        with gr.Column(scale=1):
+            gr.Markdown("### 1 — API & Model Settings")
+
+            llm_key_input = gr.Textbox(
+                label="LLM API Key",
+                placeholder="OpenAI or compatible key",
+                type="password",
+            )
+
+            base_url = gr.Textbox(
+                label="LLM Base URL",
+                value="https://api.openai.com",
+                placeholder="e.g. https://api.openai.com",
+            )
+
+            model_name = gr.Textbox(
+                label="Model Name",
+                value="gpt-4.1",
+                placeholder="e.g. gpt-4.1, gpt-4o, etc.",
+            )
+
+            gr.Markdown("#### Optional — Firecrawl (URL Scraper)")
+            firecrawl_key = gr.Textbox(
+                label="Firecrawl API Key (optional)",
+                placeholder="Only needed if you want automatic URL scraping",
+                type="password",
+            )
+
+            gr.Markdown("#### Sample Config")
+            sample_dropdown = gr.Dropdown(
+                label="Load a sample scenario",
+                choices=list(SAMPLE_CONFIGS.keys()),
+                value=None,
+            )
+            load_sample_btn = gr.Button("Load Sample")
+
+        # RIGHT: content + config
+        with gr.Column(scale=2):
+            gr.Markdown("### 2 — Content & Focus")
+
+            url_input = gr.Textbox(
+                label="Source URL",
+                placeholder="Paste a URL to analyze (works best with Firecrawl key, but optional)",
+            )
+
+            pasted_text = gr.Textbox(
+                label="Or paste content manually",
+                placeholder="Paste article text, notes, or report sections here.",
+                lines=8,
+            )
+
+            user_notes = gr.Textbox(
+                label="Your context / what you care about",
+                placeholder="Example: Focus on youth workforce impacts and funding opportunities.",
+                lines=3,
+            )
+
+            focus = gr.Dropdown(
+                label="Focus lens",
+                choices=[
+                    "Policy / Regulation",
+                    "Product / Market",
+                    "Industry / Strategy",
+                    "Risk & Compliance",
+                    "Custom / Other",
+                ],
+                value="Industry / Strategy",
+            )
+
+            generate_btn = gr.Button("🚀 Generate Insight Brief", variant="primary")
+
+    gr.Markdown("### 3 — Executive Brief")
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            brief_md = gr.Markdown(
+                label="Brief",
+                value="Your executive brief will appear here after generation.",
+            )
+        with gr.Column(scale=2):
+            brief_json = gr.Code(
+                label="Raw JSON (for automation / export)",
+                language="json",
+            )
+
+    gr.Markdown("### 4 — Insight Density Visual")
+    brief_fig = gr.Plot(label="Insight Density by Category")
+
+    # Wiring
+    load_sample_btn.click(
+        load_sample,
+        inputs=[sample_dropdown],
+        outputs=[url_input, user_notes, focus],
+    )
+
+    generate_btn.click(
+        generate_brief_ui,
+        inputs=[
+            llm_key_state,
+            llm_key_input,
+            base_url,
+            model_name,
+            firecrawl_key,
+            url_input,
+            pasted_text,
+            user_notes,
+            focus,
+        ],
+        outputs=[brief_md, brief_json, brief_fig, llm_key_state],
+    )
+
+if __name__ == "__main__":
+    demo.launch()