commit 7fe682e97e533c0238287f42c48a72e4e5597618
Author: Илья 5f1b81b8-4f5d-11e8-9c2d-fa7ae01bbebc <gurevich1104@mail.ru>
Date:   Sat Jun 27 13:51:03 2026 +0000

    add: main.py

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..b2e3232
--- /dev/null
+++ b/main.py
@@ -0,0 +1,146 @@
+import os
+import asyncio
+import argparse
+from pathlib import Path
+
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_chroma import Chroma
+from langchain_core.documents import Document
+from langchain.tools import tool
+from deepagents import create_deep_agent
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+
+# -------------------- 1. LLM and Embeddings --------------------
+llm = ChatOpenAI(
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+    temperature=0.0,
+)
+
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+# -------------------- 2. Chroma DB --------------------
+CHROMA_PATH = Path("./chroma_faq")
+CHROMA_COLLECTION = "course_faq"
+
+vector_store = Chroma(
+    collection_name=CHROMA_COLLECTION,
+    embedding_function=embeddings,
+    persist_directory=str(CHROMA_PATH),
+)
+
+# Persist changes
+vector_store.persist()
+
+# -------------------- 3. Tools --------------------
+@tool
+def search_knowledge(query: str) -> str:
+    """Search the knowledge base for relevant information."""
+    docs = vector_store.similarity_search(query, k=3)
+    return "\n".join(d.page_content for d in docs) if docs else "No results found in course materials."
+
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Fetch course metadata (schedule, syllabus, etc.) from a static JSON file."""
+    meta_path = Path("meta.json")
+    if not meta_path.exists():
+        return "Metadata file not found."
+    import json
+    data = json.loads(meta_path.read_text())
+    query_lower = query.lower()
+    if "schedule" in query_lower:
+        return f"Course schedule: {data.get('schedule', 'Not available')}"
+    if "syllabus" in query_lower:
+        return f"Syllabus URL: {data.get('syllabus_url', 'Not available')}"
+    if "instructor" in query_lower:
+        return f"Instructor: {data.get('instructor', 'Not available')}"
+    # Default: return all
+    return json.dumps(data, indent=2)
+
+# -------------------- 4. Backend --------------------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
+
+# -------------------- 5. Agent --------------------
+SYSTEM_PROMPT = (
+    "You are a helpful FAQ bot for the course.\n"
+    "Use the 'search_knowledge' tool to answer questions about course materials.\n"
+    "Use the 'fetch_course_meta' tool for questions about schedule, syllabus, instructor, etc.\n"
+    "Do not call both tools unnecessarily.\n"
+    "In your final answer, prepend 'source: chroma' or 'source: mcp_meta' to indicate which tool provided the information."
+)
+
+agent = create_deep_agent(
+    model=llm,
+    tools=[search_knowledge, fetch_course_meta],
+    backend=backend,
+    system_prompt=SYSTEM_PROMPT,
+)
+
+# -------------------- 6. Data Loader --------------------
+
+def load_faq_to_chroma():
+    data_dir = Path("data")
+    if not data_dir.exists():
+        data_dir.mkdir()
+        # Create sample markdown files if missing
+        (data_dir / "file1.md").write_text(
+            "## Course Overview\nThis course covers advanced topics in AI. Topics include machine learning, deep learning, and natural language processing."
+        )
+        (data_dir / "file2.md").write_text(
+            "## FAQ\nQ: What is the schedule?\nA: Sessions are held on Mondays and Wednesdays.\nQ: Where can I find the syllabus?\nA: Syllabus is available on the course website."
+        )
+    docs = []
+    for md_file in data_dir.glob("*.md"):
+        text = md_file.read_text()
+        docs.append(Document(page_content=text, metadata={"source": md_file.name}))
+    vector_store.add_documents(docs)
+    vector_store.persist()
+    print(f"Loaded {len(docs)} documents into Chroma collection '{CHROMA_COLLECTION}'.")
+
+# -------------------- 7. CLI --------------------
+PRESET_QUESTIONS = {
+    "1": "What topics are covered in the course?",
+    "2": "Where can I find the syllabus?",
+    "3": "What is the course schedule?",
+}
+
+async def run_question(question: str, thread_id: str = "session-1"):
+    result = await agent.ainvoke(
+        {"messages": ["HumanMessage(content=\"{}\")".format(question)]},
+        {"configurable": {"thread_id": thread_id}},
+    )
+    # The agent returns a dict with 'messages'; extract last message
+    content = result["messages"][-1].content
+    print(content)
+
+async def main():
+    # Ensure data is loaded
+    load_faq_to_chroma()
+
+    parser = argparse.ArgumentParser(description="FAQ Bot CLI")
+    parser.add_argument("--preset", choices=["1", "2", "3"], help="Run a preset question")
+    args = parser.parse_args()
+
+    if args.preset:
+        question = PRESET_QUESTIONS[args.preset]
+        print(f"Preset question {args.preset}: {question}")
+        await run_question(question)
+    else:
+        print("Enter your question (type 'exit' to quit):")
+        while True:
+            q = input("> ")
+            if q.lower() in {"exit", "quit"}:
+                break
+            if q.strip():
+                await run_question(q)
+
+if __name__ == "__main__":
+    asyncio.run(main())