weitere anpassungen des Retrivals

math-tutor/backend/app/deterministic_services/context_store.py

@@ -7,6 +7,8 @@ from datetime import datetime
 from threading import Lock
 from typing import Any
 
+from app.deterministic_services import Source
+
 
 _CACHE: dict[str, dict[str, Any]] = {}
 _LOCK = Lock()
@@ -74,10 +76,9 @@ def update_history(sheet: dict[str, Any], messages: list[dict]) -> None:
 def add_retrieval_context(
     sheet: dict[str, Any],
     query: str,
-    context: str,
-    sources: list[dict],
+    sources: list[Source],
 ) -> None:
-    retrieval_entry = {"query": query, "context": context, "sources": sources}
+    retrieval_entry = {"query": query, "sources": [source.to_string() for source in sources]}
     sheet["retrieval_contexts"].append(retrieval_entry)
     sheet["updated_at"] = _utc_now()
 
@@ -85,14 +86,12 @@ def add_retrieval_context(
 def update_retrieval_context(
     sheet: dict[str, Any],
     query: str,
-    context: str,
-    sources: list[dict],
+    sources: list[Source],
 ) -> None:
     retrievals = sheet.get("retrieval_contexts", [])
     if retrievals:
         latest_retrieval = retrievals[-1]
-        latest_retrieval["context"] = context
-        latest_retrieval["sources"] = sources
+        latest_retrieval["sources"] = [source.to_string() for source in sources]
         latest_retrieval["query"] = query
         sheet["updated_at"] = _utc_now()
 

math-tutor/backend/app/deterministic_services/orchestrator.py

@@ -13,15 +13,15 @@ def _append_tool_log(tool_log: list[dict], name: str, args: dict, response: obje
 
 def _bootstrap_context(sheet: dict, query_text: str, tool_log: list[dict]) -> None:
     # Erstelle einen neuen Retrieval-Block oder aktualisiere den bestehenden
-    context, sources = retrieval_service.retrieve_context(query_text=query_text)
+    sources = retrieval_service.retrieve_context(query_text=query_text)
     
     retrievals = sheet.get("retrieval_contexts", [])
     if retrievals:
-        context_store.update_retrieval_context(sheet, query_text, context, sources)
-        _append_tool_log(tool_log, "update_retrieve_context", {"query": query_text}, {"context": context, "sources": sources})
+        context_store.update_retrieval_context(sheet, query_text, sources)
+        _append_tool_log(tool_log, "update_retrieve_context", {"query": query_text}, {"sources": [source.to_string() for source in sources]})
     else:
-        context_store.add_retrieval_context(sheet, query_text, context, sources)
-        _append_tool_log(tool_log, "retrieve_context", {"query": query_text}, {"context": context, "sources": sources})
+        context_store.add_retrieval_context(sheet, query_text, sources)
+        _append_tool_log(tool_log, "retrieve_context", {"query": query_text}, {"sources": [source.to_string() for source in sources]})
     
     math_request = math_intent_LLM.extract_math_request(query_text)
     if math_request:

math-tutor/backend/app/deterministic_services/retrieval_service.py

 from __future__ import annotations
 
-from typing import List
+from collections import defaultdict
+from typing import Dict, List
 
+from app.deterministic_services import Source
 from app import config
 from app.deterministic_services.embeddings import OpenAILikeEmbeddings
 from app.deterministic_services import vector_store
 
-CONTEXT_LIMITS = {
-    "direct": 4,
-    "indirect": 6,
-    "subsection": 2,
-    "section": 1,
-}
-
-
 def _get_embedder() -> OpenAILikeEmbeddings:
     settings = config.get_embedding_settings()
     return OpenAILikeEmbeddings(
@@ -24,73 +18,14 @@ def _get_embedder() -> OpenAILikeEmbeddings:
     )
 
 
-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 _append_group(
-    label: str,
-    items: List[vector_store.Retrieved],
-    limit: int,
-    blocks: List[str],
-    sources: List[dict],
-) -> None:
-    if not items:
-        return
-    for doc in items[:limit]:
-        ref = _format_ref(doc)
-        blocks.append(f"{label} {ref}\n{doc.markdown}")
-        sources.append({
-            "ref": ref,
-            "context": doc.markdown,
-            "score": doc.score,
-            "label": label
-        })
-
-
-def build_context(result: dict) -> tuple[str, List[dict]]:
-    blocks: List[str] = []
-    sources: List[dict] = []
-
-    _append_group("DIRECT", result.get("children_direct", []), CONTEXT_LIMITS["direct"], blocks, sources)
-    _append_group("INDIRECT", result.get("children_expanded", []), CONTEXT_LIMITS["indirect"], blocks, sources)
-    _append_group("SUBSECTION", result.get("subsections", []), CONTEXT_LIMITS["subsection"], blocks, sources)
-    _append_group("SECTION", result.get("sections", []), CONTEXT_LIMITS["section"], blocks, sources)
-
-    if not blocks:
-        return "KONTEXT: (leer)", sources
-    return "KONTEXT:\n" + "\n\n".join(blocks), sources
-
-
-def retrieve_context(query_text: str, pg_url: str | None = None) -> tuple[str, List[dict]]:
+def retrieve_context(query_text: str, pg_url: str | None = None) -> List[Source]:
     url = pg_url or config.get_postgres_url()
     embedder = _get_embedder()
-    retrieval = vector_store.retrieve(
+    sources = vector_store.retrieve(
         pg_url=url,
         embedder=embedder,
         query=query_text,
         k=8,
         expand_links=True,
     )
-    return build_context(retrieval)
+    return sources