Update app.py

app.py

@@ -1,136 +1,242 @@
+import io
+import os
+import base64
+from typing import List, Dict, Tuple
+
 import gradio as gr
 from openai import OpenAI
-from typing import List, Dict
 
-# ----------------------------
+# Optional parsers
+import pandas as pd
+from pypdf import PdfReader
+from docx import Document as DocxDocument
+
+# ===============================
 # Client
-# ----------------------------
+# ===============================
 def get_client(key: str) -> OpenAI:
     key = (key or "").strip()
     if not key:
         raise gr.Error("Please enter your OpenAI API key.")
     return OpenAI(api_key=key)
 
-# ----------------------------
-# GPT-5 Chat (messages format)
-# ----------------------------
-def chat_handle(api_key: str, user_input: str, history: List[Dict]):
-
-    # Ensure history is a list of {"role": "...", "content": "..."}
+# ===============================
+# Chat (messages format + streaming)
+# ===============================
+def stream_chat(api_key: str, user_input: str, history: List[Dict]):
+    client = get_client(api_key)
     history = history or []
     user_input = (user_input or "").strip()
     if not user_input:
-        # no change; just return existing state and clear the input
         return history, history, gr.update(value="")
 
-    client = get_client(api_key)
-
-    # Append the user message to conversation state used for the API call
     msgs = history + [{"role": "user", "content": user_input}]
-
     try:
         stream = client.chat.completions.create(
             model="gpt-5",
             messages=msgs,
             stream=True,
         )
-
-        # Stream assistant tokens and update the UI
-        assistant_accum = ""
-        # While streaming we show a *temporary* assistant message
+        acc = ""
         for chunk in stream:
             delta = chunk.choices[0].delta.content or ""
-            assistant_accum += delta
-            # Show msgs plus the in-progress assistant message
-            yield (msgs + [{"role": "assistant", "content": assistant_accum}]), msgs, gr.update(value="")
-
-        # On completion, commit the assistant message to history
-        final_history = msgs + [{"role": "assistant", "content": assistant_accum}]
-        yield final_history, final_history, gr.update(value="")
-
+            acc += delta
+            yield msgs + [{"role": "assistant", "content": acc}], msgs, gr.update(value="")
+        final_hist = msgs + [{"role": "assistant", "content": acc}]
+        yield final_hist, final_hist, gr.update(value="")
     except Exception as e:
         err = f"[Error] {e}"
-        final_history = msgs + [{"role": "assistant", "content": err}]
-        yield final_history, final_history, gr.update(value="")
-
-# ----------------------------
-# Code Assistant (Explain / Refactor)
-# ----------------------------
-def analyze_code(api_key: str, code_snippet: str, mode: str) -> str:
-    client = get_client(api_key)
-    code = (code_snippet or "").strip()
-    if not code:
-        raise gr.Error("Paste some code first.")
-
-    if mode == "Explain & Improve":
-        prompt = (
-            "You are an expert software engineer. Explain the following code clearly, "
-            "point out issues, and propose concrete improvements with rationale. "
-            "If relevant, show a revised snippet.\n\n"
-            f"{code}"
-        )
-    else:
-        prompt = (
-            "You are an expert software engineer. Refactor the following code for clarity, "
-            "performance, error handling, and maintainability. Keep the same behavior. "
-            "Return the improved code first, then a short summary of changes.\n\n"
-            f"{code}"
-        )
-
+        final_hist = msgs + [{"role": "assistant", "content": err}]
+        yield final_hist, final_hist, gr.update(value="")
+
+# ===============================
+# Pro Brief – File ingestion
+# ===============================
+TEXT_EXTS = {".txt", ".md", ".markdown"}
+DOCX_EXTS = {".docx"}
+PDF_EXTS  = {".pdf"}
+CSV_EXTS  = {".csv"}
+
+def _ext(path: str) -> str:
+    return os.path.splitext(path.lower())[1]
+
+def read_text_file(fp: str) -> str:
+    # Try utf-8, fallback to latin-1
     try:
+        with open(fp, "r", encoding="utf-8") as f:
+            return f.read()
+    except UnicodeDecodeError:
+        with open(fp, "r", encoding="latin-1") as f:
+            return f.read()
+
+def read_pdf(fp: str) -> str:
+    text = []
+    with open(fp, "rb") as f:
+        reader = PdfReader(f)
+        for page in reader.pages:
+            txt = page.extract_text() or ""
+            text.append(txt)
+    return "\n".join(text).strip()
+
+def read_docx(fp: str) -> str:
+    doc = DocxDocument(fp)
+    return "\n".join([p.text for p in doc.paragraphs]).strip()
+
+def summarize_csv(fp: str) -> str:
+    # Compute useful stats and include a small sampling; return as text for the LLM
+    try:
+        df = pd.read_csv(fp)
+    except Exception:
+        # fallback: try semicolon or tab
+        try:
+            df = pd.read_csv(fp, sep=";")
+        except Exception:
+            df = pd.read_csv(fp, sep="\t")
+
+    shape_info = f"Rows: {df.shape[0]}, Columns: {df.shape[1]}"
+    cols = ", ".join([f"{c} ({str(df[c].dtype)})" for c in df.columns])
+    desc = df.describe(include="all").transpose().fillna("").to_string()
+    head = df.head(10).to_string(index=False)
+
+    return (
+        "CSV SUMMARY\n"
+        f"{shape_info}\n\n"
+        f"COLUMNS & TYPES:\n{cols}\n\n"
+        f"DESCRIBE():\n{desc}\n\n"
+        f"FIRST 10 ROWS:\n{head}\n"
+    )
+
+def load_files(files: List[gr.File]) -> Tuple[str, List[str]]:
+    if not files:
+        raise gr.Error("Please upload at least one file (PDF, DOCX, TXT, MD, or CSV).")
+    texts = []
+    names = []
+    for f in files:
+        path = f.name
+        names.append(os.path.basename(path))
+        ext = _ext(path)
+        if ext in TEXT_EXTS:
+            texts.append(read_text_file(path))
+        elif ext in PDF_EXTS:
+            texts.append(read_pdf(path))
+        elif ext in DOCX_EXTS:
+            texts.append(read_docx(path))
+        elif ext in CSV_EXTS:
+            texts.append(summarize_csv(path))
+        else:
+            raise gr.Error(f"Unsupported file type: {ext}")
+    return "\n\n-----\n\n".join(texts), names
+
+# ===============================
+# Pro Brief – Chunking & synthesis
+# ===============================
+def chunk_text(s: str, max_chars: int = 12000) -> List[str]:
+    s = s.strip()
+    if len(s) <= max_chars:
+        return [s]
+    chunks = []
+    start = 0
+    while start < len(s):
+        end = min(start + max_chars, len(s))
+        # try to break on paragraph boundary
+        cut = s.rfind("\n\n", start, end)
+        if cut == -1 or cut <= start + 2000:
+            cut = end
+        chunks.append(s[start:cut])
+        start = cut
+    return chunks
+
+def llm_summarize_chunks(client: OpenAI, chunks: List[str], mode: str, custom_note: str) -> List[str]:
+    summaries = []
+    for i, ch in enumerate(chunks, start=1):
+        mode_prompt = {
+            "Executive Brief": (
+                "Create a crisp executive brief with sections: Context, Key Findings, Metrics, Implications, Decisions Needed."
+            ),
+            "Action Items": (
+                "Extract actionable tasks with owners (if available), deadlines (if implied), dependencies, and priority."
+            ),
+            "Risks & Mitigations": (
+                "Identify key risks, likelihood, impact, and concrete mitigations. Include watchpoints and triggers."
+            ),
+            "Meeting Minutes": (
+                "Produce clean, structured minutes: Attendees (if inferable), Agenda, Discussion, Decisions, Action Items."
+            ),
+            "JSON Summary": (
+                "Return a compact JSON with keys: context, findings[], metrics{}, actions[], risks[], decisions[]."
+            ),
+        }[mode]
+
+        sys = "You are a senior analyst. Write succinctly; use bullet points where appropriate."
+        usr = f"{mode_prompt}\n\n{('Additional guidance: ' + custom_note) if custom_note else ''}\n\n---\nSOURCE CHUNK {i}/{len(chunks)}:\n{ch}\n"
         resp = client.chat.completions.create(
             model="gpt-5",
-            messages=[
-                {"role": "system", "content": "You communicate clearly and concisely to advanced developers."},
-                {"role": "user", "content": prompt},
-            ],
+            messages=[{"role": "system", "content": sys},
+                      {"role": "user", "content": usr}],
         )
-        return resp.choices[0].message.content
-    except Exception as e:
-        raise gr.Error(f"Code analysis failed: {e}")
+        summaries.append(resp.choices[0].message.content.strip())
+    return summaries
+
+def llm_synthesize_final(client: OpenAI, mode: str, names: List[str], partials: List[str], custom_note: str) -> str:
+    sys = "You are a chief of staff producing board-ready output. Tight, accurate, and well-structured."
+    corpus = "\n\n---\n\n".join([f"[PART {i+1}]\n{p}" for i, p in enumerate(partials)])
+    usr = (
+        f"Files analyzed: {', '.join(names)}\n\n"
+        f"Mode: {mode}\n"
+        f"{('Additional guidance: ' + custom_note) if custom_note else ''}\n\n"
+        "Synthesize the PARTS into a single cohesive deliverable. If JSON mode, return only JSON."
+        "\n\n---\nCORPUS (SUMMARIES):\n" + corpus
+    )
+    resp = client.chat.completions.create(
+        model="gpt-5",
+        messages=[{"role": "system", "content": sys},
+                  {"role": "user", "content": usr}],
+    )
+    return resp.choices[0].message.content.strip()
+
+def pro_brief(api_key: str, files: List[gr.File], mode: str, custom_note: str) -> str:
+    client = get_client(api_key)
+    raw_text, names = load_files(files)
+    chunks = chunk_text(raw_text, max_chars=12000)
+    partials = llm_summarize_chunks(client, chunks, mode, custom_note)
+    final = llm_synthesize_final(client, mode, names, partials, custom_note)
+    return final
 
-# ----------------------------
+# ===============================
 # UI
-# ----------------------------
-with gr.Blocks(title="ZEN GPT-5 Production SDK") as demo:
+# ===============================
+with gr.Blocks(title="ZEN GPT-5 • Production Tools") as demo:
     gr.Markdown("### 🔐 Enter your OpenAI API key (not stored)")
     api_key = gr.Textbox(placeholder="sk-...", type="password", label="OpenAI API Key")
 
     with gr.Tab("💬 Chat"):
         chatbox = gr.Chatbot(label="GPT-5 Chat", height=420, type="messages")
-        history_state = gr.State([])  # list[dict(role, content)]
+        history_state = gr.State([])
         user_in = gr.Textbox(placeholder="Say hi…", label="Message")
         send_btn = gr.Button("Send", variant="primary")
         clear_btn = gr.Button("Clear Chat")
 
-        # Wire up: send triggers streaming; we update chatbox + state + clear input
-        send_btn.click(
-            chat_handle,
-            inputs=[api_key, user_in, history_state],
-            outputs=[chatbox, history_state, user_in],
-            queue=True,
-        )
-        user_in.submit(
-            chat_handle,
-            inputs=[api_key, user_in, history_state],
-            outputs=[chatbox, history_state, user_in],
-            queue=True,
-        )
-        clear_btn.click(lambda: ([], []), inputs=None, outputs=[chatbox, history_state])
+        send_btn.click(stream_chat, [api_key, user_in, history_state], [chatbox, history_state, user_in], queue=True)
+        user_in.submit(stream_chat, [api_key, user_in, history_state], [chatbox, history_state, user_in], queue=True)
+        clear_btn.click(lambda: ([], []), None, [chatbox, history_state])
 
-    with gr.Tab("💻 Code Assistant"):
-        gr.Markdown("Use GPT-5 to **explain or refactor** any code.")
+    with gr.Tab("📄 Pro Brief (Docs → Executive Output)"):
+        gr.Markdown(
+            "Upload PDFs, DOCX, TXT, MD, or CSV. Get an **Executive Brief**, **Action Items**, "
+            "**Risks & Mitigations**, **Meeting Minutes**, or a **JSON Summary**."
+        )
+        files = gr.File(label="Upload files", file_count="multiple", type="filepath")
         mode = gr.Radio(
-            ["Explain & Improve", "Refactor Only"],
-            value="Explain & Improve",
-            label="Mode"
+            ["Executive Brief", "Action Items", "Risks & Mitigations", "Meeting Minutes", "JSON Summary"],
+            value="Executive Brief",
+            label="Output Mode",
         )
-        code_input = gr.Code(label="Paste your code", language="python", lines=20)
-        run_btn = gr.Button("Analyze Code", variant="primary")
-        result = gr.Textbox(label="Result", lines=20)
-        run_btn.click(analyze_code, [api_key, code_input, mode], result)
+        custom = gr.Textbox(label="Optional guidance (tone, audience, focus areas)", lines=3, placeholder="e.g., Board-ready; focus on budget impact and timeline risk.")
+        run = gr.Button("Generate Pro Brief", variant="primary")
+        out = gr.Markdown(label="Output", show_copy_button=True)
+        run.click(pro_brief, [api_key, files, mode, custom], out)
 
-    # Subtle program stamp (bottom-right)
+    # Subtle program stamp
     gr.HTML(
         "<div style='text-align:right; font-size:12px; opacity:0.55; margin-top:10px;'>"
         "Module 3 – ZEN SDK Production"