Create app.py

app.py

@@ -0,0 +1,118 @@
+import os
+from pathlib import Path
+import gradio as gr
+
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
+from llama_index.llms.openai import OpenAI
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+
+# ======================
+# Config (safe defaults)
+# ======================
+MODEL = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+EMBED_MODEL = os.getenv("OPENAI_EMBED_MODEL", "text-embedding-3-small")
+TOP_K = int(os.getenv("TOP_K", "3"))
+
+# Your knowledge base file in the Space repo
+DOC_PATH = Path(os.getenv("DOC_PATH", "challenge_context.txt"))
+
+SYSTEM_GUARDRAILS = (
+    "You are Challenge Copilot. Answer ONLY using the provided context. "
+    "If the answer is not in the context, say: 'I don’t know based on the current document.' "
+    "Then ask the user to add the missing official details to challenge_context.txt."
+)
+
+
+# ======================
+# Build index (cached)
+# ======================
+_INDEX = None
+_QUERY_ENGINE = None
+
+def build_index():
+    global _INDEX, _QUERY_ENGINE
+
+    if _QUERY_ENGINE is not None:
+        return _QUERY_ENGINE
+
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
+        raise RuntimeError(
+            "OPENAI_API_KEY is missing. Add it in the Space Settings → Variables and secrets."
+        )
+
+    if not DOC_PATH.exists():
+        # Create a placeholder so the Space boots even if you forgot the file
+        DOC_PATH.write_text(
+            "Add the official Building AI Application Challenge content here.\n",
+            encoding="utf-8",
+        )
+
+    # LlamaIndex global settings
+    Settings.llm = OpenAI(model=MODEL, temperature=0.2)
+    Settings.embed_model = OpenAIEmbedding(model=EMBED_MODEL)
+    Settings.chunk_size = 800
+    Settings.chunk_overlap = 120
+
+    # Reader expects a directory
+    data_dir = str(DOC_PATH.parent)
+    docs = SimpleDirectoryReader(
+        input_dir=data_dir,
+        required_exts=[".txt"],
+        recursive=False
+    ).load_data()
+
+    # Only index the target file
+    docs = [d for d in docs if d.metadata.get("file_name") == DOC_PATH.name]
+    if not docs:
+        raise FileNotFoundError(f"Could not load {DOC_PATH.name}. Make sure it exists in the repo.")
+
+    _INDEX = VectorStoreIndex.from_documents(docs)
+    _QUERY_ENGINE = _INDEX.as_query_engine(similarity_top_k=TOP_K)
+    return _QUERY_ENGINE
+
+
+def format_sources(resp, max_sources=3, max_chars=220):
+    lines = []
+    for i, sn in enumerate(getattr(resp, "source_nodes", [])[:max_sources], start=1):
+        fn = sn.node.metadata.get("file_name", "unknown")
+        snippet = sn.node.get_content().replace("\n", " ").strip()[:max_chars]
+        score = getattr(sn, "score", None)
+        score_txt = f" (score={score:.3f})" if isinstance(score, (float, int)) else ""
+        lines.append(f"{i}. {fn}{score_txt}: {snippet}...")
+    return "\n".join(lines) if lines else "No sources returned."
+
+
+def chat(message, history):
+    qe = build_index()
+
+    prompt = (
+        f"{SYSTEM_GUARDRAILS}\n\n"
+        f"User question: {message}\n"
+        f"Answer using ONLY the context."
+    )
+    resp = qe.query(prompt)
+    answer = str(resp).strip()
+
+    show_sources = os.getenv("SHOW_SOURCES", "true").lower() == "true"
+    if show_sources:
+        answer += "\n\n---\nSources:\n" + format_sources(resp, max_sources=TOP_K)
+
+    return answer
+
+
+demo = gr.ChatInterface(
+    fn=chat,
+    title="Challenge Copilot — RAG Q&A Bot",
+    description="Ask questions about the Building AI Application Challenge using challenge_context.txt (LlamaIndex + OpenAI).",
+    examples=[
+        "What will I build in this live session?",
+        "Who is this best for?",
+        "What are the prerequisites?"
+    ],
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    demo.launch()