rm unnecessery files

math-tutor/backend/app/api/chat.py

@@ -3,13 +3,11 @@ from __future__ import annotations
 from typing import List, Optional
 
 import os
-import httpx
 from fastapi import APIRouter, HTTPException
 from dotenv import load_dotenv
 from pydantic import BaseModel, Field
 
-from app.services.embeddings import OpenAILikeEmbeddings
-from app.services import vector_store
+from app.services import chat_engine
 
 router = APIRouter()
 
@@ -17,20 +15,6 @@ load_dotenv()
 
 OPENAI_BASE_URL = os.getenv("OPENAI_BASE_URL")
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-OPENAI_MODEL = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
-
-SYSTEM_PROMPT = """Du bist ein Mathe-Tutor. Antworte auf Deutsch, klar und korrekt.
-Nutze ausschließlich den bereitgestellten Kontext. Wenn nichts zur Frage im Kontext steht, antworte mit "Dazu steht nichts im Material" und nichts weiter.
-Gib wenn möglich eine kurze Struktur: (1) Idee, (2) Definition, (3) kurzer Begründungs-/Rechenweg, (4) Mini-Beispiel.
-Zitiere Quellen inline mit den eckigen Klammern, die im Kontext vorangestellt sind, z.B. [s2/ss1/c3 | definition | ...].
-"""
-
-CONTEXT_LIMITS = {
-    "direct": 4,
-    "indirect": 6,
-    "subsection": 2,
-    "section": 1,
-}
 
 
 class ChatMessage(BaseModel):
@@ -48,59 +32,6 @@ class ChatResponse(BaseModel):
     sources: List[str] = []
 
 
-def _get_embedder() -> OpenAILikeEmbeddings:
-    base_url = os.getenv("OPENAI_BASE_URL")
-    api_key = os.getenv("OPENAI_API_KEY")
-    model = os.getenv("OPENAI_EMBED_MODEL", "text-embedding-3-large")
-    if not base_url or not api_key:
-        raise HTTPException(status_code=500, detail="Missing OPENAI_BASE_URL or OPENAI_API_KEY")
-    return OpenAILikeEmbeddings(base_url=base_url, api_key=api_key, model=model, target_dim=1024)
-
-
-def _format_ref(doc: vector_store.Retrieved) -> str:
-    meta = doc.metadata
-    sec = meta.get("section_index")
-    sub = meta.get("subsection_index")
-    child = meta.get("child_index")
-    ref = []
-    if sec is not None:
-        ref.append(f"s{sec}")
-    if sub is not None:
-        ref.append(f"ss{sub}")
-    if child is not None:
-        ref.append(f"c{child}")
-    ref_id = "/".join(ref) if ref else "unknown"
-
-    doc_type = meta.get("type") or doc.doc_type
-    title = (
-        meta.get("title")
-        or meta.get("subsection_title")
-        or meta.get("section_title")
-        or meta.get("path")
-        or "Untitled"
-    )
-    return f"[{ref_id} | {doc_type} | {title}]"
-
-
-def _build_context(result: dict) -> str:
-    blocks: List[str] = []
-
-    def add_group(label: str, items: List[vector_store.Retrieved], limit: int) -> None:
-        if not items:
-            return
-        for doc in items[:limit]:
-            blocks.append(f"{label} {_format_ref(doc)}\n{doc.markdown}")
-
-    add_group("DIRECT", result.get("children_direct", []), CONTEXT_LIMITS["direct"])
-    add_group("INDIRECT", result.get("children_expanded", []), CONTEXT_LIMITS["indirect"])
-    add_group("SUBSECTION", result.get("subsections", []), CONTEXT_LIMITS["subsection"])
-    add_group("SECTION", result.get("sections", []), CONTEXT_LIMITS["section"])
-
-    if not blocks:
-        return "KONTEXT: (leer)"
-    return "KONTEXT:\n" + "\n\n".join(blocks)
-
-
 @router.post("/api/chat", response_model=ChatResponse)
 def chat(request: ChatRequest) -> ChatResponse:
     if not request.messages:
@@ -111,41 +42,19 @@ def chat(request: ChatRequest) -> ChatResponse:
         reply = f"Mock reply to: {last.text}"
         return ChatResponse(reply=reply, sources=["doc:example"])
 
-    pg_url = os.getenv("POSTGRES_URL")
-    if not pg_url:
-        raise HTTPException(status_code=500, detail="Missing POSTGRES_URL")
-
-    query_text = request.messages[-1].text
-    embedder = _get_embedder()
-    retrieval = vector_store.retrieve(
-        pg_url=pg_url,
-        embedder=embedder,
-        query=query_text,
-        k=8,
-        expand_links=True,
-    )
-    context_block = _build_context(retrieval)
-
-    messages_payload = [
-        {"role": "system", "content": SYSTEM_PROMPT},
-        {"role": "system", "content": context_block},
-    ] + [{"role": message.role, "content": message.text} for message in request.messages]
-
-    payload = {
-        "model": OPENAI_MODEL,
-        "messages": messages_payload,
-    }
-
-    headers = {"Authorization": f"Bearer {OPENAI_API_KEY}"}
-    url = f"{OPENAI_BASE_URL.rstrip('/')}/v1/chat/completions"
-
     try:
-        with httpx.Client(timeout=60.0) as client:
-            response = client.post(url, headers=headers, json=payload)
-            response.raise_for_status()
-    except httpx.HTTPError as exc:
+        context = chat_engine.retrieve_context(
+            pg_url=os.getenv("POSTGRES_URL") or "",
+            query_text=request.messages[-1].text,
+        )
+        messages_payload = chat_engine.build_messages(
+            [{"role": m.role, "content": m.text} for m in request.messages],
+            context,
+        )
+        reply = chat_engine.call_chat_api(messages_payload)
+    except ValueError as exc:
+        raise HTTPException(status_code=500, detail=str(exc)) from exc
+    except Exception as exc:
         raise HTTPException(status_code=502, detail="chat provider failed") from exc
 
-    data = response.json()
-    reply = data["choices"][0]["message"]["content"]
     return ChatResponse(reply=reply, sources=["openai-compatible"])

math-tutor/backend/app/services/chat_engine.py

+from __future__ import annotations
+
+from typing import List
+
+import os
+import httpx
+from openai import OpenAI
+
+from app.services.embeddings import OpenAILikeEmbeddings
+from app.services import vector_store
+
+SYSTEM_PROMPT = """Du bist ein Mathe-Tutor. Antworte auf Deutsch, klar und korrekt.
+Nutze ausschließlich den bereitgestellten Kontext. Wenn nichts zur Frage im Kontext steht, antworte mit "Dazu steht nichts im Material" und nichts weiter.
+Gib wenn möglich eine kurze Struktur: (1) Idee, (2) Definition, (3) kurzer Begründungs-/Rechenweg, (4) Mini-Beispiel.
+Zitiere Quellen inline mit den eckigen Klammern, die im Kontext vorangestellt sind, z.B. [s2/ss1/c3 | definition | ...].
+"""
+
+CONTEXT_LIMITS = {
+    "direct": 8,
+    "indirect": 6,
+    "subsection": 2,
+    "section": 1,
+}
+
+
+def _get_embedder() -> OpenAILikeEmbeddings:
+    base_url = os.getenv("OPENAI_BASE_URL")
+    api_key = os.getenv("OPENAI_API_KEY")
+    model = os.getenv("OPENAI_EMBED_MODEL", "text-embedding-3-large")
+    if not base_url or not api_key:
+        raise ValueError("Missing OPENAI_BASE_URL or OPENAI_API_KEY")
+    return OpenAILikeEmbeddings(base_url=base_url, api_key=api_key, model=model, target_dim=1024)
+
+
+def _format_ref(doc: vector_store.Retrieved) -> str:
+    meta = doc.metadata
+    sec = meta.get("section_index")
+    sub = meta.get("subsection_index")
+    child = meta.get("child_index")
+    ref = []
+    if sec is not None:
+        ref.append(f"s{sec}")
+    if sub is not None:
+        ref.append(f"ss{sub}")
+    if child is not None:
+        ref.append(f"c{child}")
+    ref_id = "/".join(ref) if ref else "unknown"
+
+    doc_type = meta.get("type") or doc.doc_type
+    title = (
+        meta.get("title")
+        or meta.get("subsection_title")
+        or meta.get("section_title")
+        or meta.get("path")
+        or "Untitled"
+    )
+    return f"[{ref_id} | {doc_type} | {title}]"
+
+
+def build_context(result: dict) -> str:
+    blocks: List[str] = []
+
+    def add_group(label: str, items: List[vector_store.Retrieved], limit: int) -> None:
+        if not items:
+            return
+        for doc in items[:limit]:
+            blocks.append(f"{label} {_format_ref(doc)}\n{doc.markdown}")
+
+    add_group("DIRECT", result.get("children_direct", []), CONTEXT_LIMITS["direct"])
+    add_group("INDIRECT", result.get("children_expanded", []), CONTEXT_LIMITS["indirect"])
+    add_group("SUBSECTION", result.get("subsections", []), CONTEXT_LIMITS["subsection"])
+    add_group("SECTION", result.get("sections", []), CONTEXT_LIMITS["section"])
+
+    if not blocks:
+        return "KONTEXT: (leer)"
+    return "KONTEXT:\n" + "\n\n".join(blocks)
+
+
+def build_messages(messages: list[dict], context: str) -> list[dict]:
+    return [
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "system", "content": context},
+    ] + messages
+
+
+def retrieve_context(pg_url: str, query_text: str) -> str:
+    embedder = _get_embedder()
+    retrieval = vector_store.retrieve(
+        pg_url=pg_url,
+        embedder=embedder,
+        query=query_text,
+        k=8,
+        expand_links=True,
+    )
+    return build_context(retrieval)
+
+
+def call_chat_api(messages_payload: list[dict]) -> str:
+    base_url = os.getenv("OPENAI_BASE_URL")
+    api_key = os.getenv("OPENAI_API_KEY")
+    model = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    if not base_url or not api_key:
+        raise ValueError("Missing OPENAI_BASE_URL or OPENAI_API_KEY")
+
+    url = f"{base_url.rstrip('/')}/chat/completions"
+    payload = {
+        "model": model,
+        "messages": messages_payload,
+    }
+    headers = {"Authorization": f"Bearer {api_key}"}
+    with httpx.Client(timeout=60.0) as client:
+        response = client.post(url, headers=headers, json=payload)
+        response.raise_for_status()
+    data = response.json()
+    return data["choices"][0]["message"]["content"]
+
+
+def stream_chat(messages_payload: list[dict]):
+    base_url = os.getenv("OPENAI_BASE_URL")
+    api_key = os.getenv("OPENAI_API_KEY")
+    model = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    if not base_url or not api_key:
+        raise ValueError("Missing OPENAI_BASE_URL or OPENAI_API_KEY")
+
+    client = OpenAI(api_key=api_key, base_url=base_url)
+    return client.chat.completions.create(
+        model=model,
+        messages=messages_payload,
+        stream=True,
+    )