AI UPDATE

rag/chat.py

@@ -4,7 +4,7 @@
 import logging
 from pathlib import Path
 
-from .config import load_rag_config, RAGConfig
+from .config import load_rag_config, RAGConfig, get_service_config, ServiceConfig
 from .api_provider import get_chat_client
 from .retrieve import search_with_query
 from .user_data import build_user_soil_text, build_user_weather_text
@@ -43,6 +43,16 @@ def _load_kb_tone(kb_name: str, config: RAGConfig | None = None) -> str:
     return ""
 
 
+def _load_service_tone(service: ServiceConfig, config: RAGConfig | None = None) -> str:
+    cfg = config or load_rag_config()
+    if service.tone_file:
+        base = Path(__file__).resolve().parent.parent
+        tone_path = base / service.tone_file
+        if tone_path.exists():
+            return tone_path.read_text(encoding="utf-8").strip()
+    return _load_kb_tone(service.knowledge_base, cfg)
+
+
 def _detect_kb_intent(query: str) -> str:
     """تشخیص ساده نوع پایگاه دانش مورد نیاز از روی متن سوال."""
     q = query.lower()
@@ -59,10 +69,11 @@ def _detect_kb_intent(query: str) -> str:
 
 def build_rag_context(
     query: str,
-    sensor_uuid: str,
+    sensor_uuid: str | None = None,
     config: RAGConfig | None = None,
     limit: int = 8,
     kb_name: str | None = None,
+    service_id: str | None = None,
 ) -> str:
     """
     ساخت context برای LLM: دیتای فعلی خاک کاربر + متن‌های مرتبط از RAG.
@@ -76,24 +87,34 @@ def build_rag_context(
         len(query or ""),
     )
     parts: list[str] = []
+    cfg = config or load_rag_config()
+    service = get_service_config(service_id, cfg) if service_id else None
+    include_user_embeddings = service.use_user_embeddings if service else True
+    resolved_kb_name = kb_name or (service.knowledge_base if service else None)
 
-    user_soil = build_user_soil_text(sensor_uuid)
-    if user_soil and user_soil.strip():
-        parts.append("[داده‌های فعلی خاک شما]\n" + user_soil.strip())
-        logger.debug("Included user soil section sensor_uuid=%s", sensor_uuid)
-    else:
-        logger.info("No user soil data found sensor_uuid=%s", sensor_uuid)
+    if include_user_embeddings and sensor_uuid:
+        user_soil = build_user_soil_text(sensor_uuid)
+        if user_soil and user_soil.strip():
+            parts.append("[داده‌های فعلی خاک شما]\n" + user_soil.strip())
+            logger.debug("Included user soil section sensor_uuid=%s", sensor_uuid)
+        else:
+            logger.info("No user soil data found sensor_uuid=%s", sensor_uuid)
 
-    weather_text = build_user_weather_text(sensor_uuid)
-    if weather_text and weather_text.strip():
-        parts.append("[پیش‌بینی هواشناسی]\n" + weather_text.strip())
-        logger.debug("Included weather section sensor_uuid=%s", sensor_uuid)
-    else:
-        logger.info("No weather data found sensor_uuid=%s", sensor_uuid)
+        weather_text = build_user_weather_text(sensor_uuid)
+        if weather_text and weather_text.strip():
+            parts.append("[پیش‌بینی هواشناسی]\n" + weather_text.strip())
+            logger.debug("Included weather section sensor_uuid=%s", sensor_uuid)
+        else:
+            logger.info("No weather data found sensor_uuid=%s", sensor_uuid)
 
     results = search_with_query(
-        query, sensor_uuid=sensor_uuid, limit=limit, config=config,
-        kb_name=kb_name,
+        query,
+        sensor_uuid=sensor_uuid,
+        limit=limit,
+        config=cfg,
+        kb_name=resolved_kb_name,
+        service_id=service_id,
+        use_user_embeddings=include_user_embeddings,
     )
     if results:
         logger.info("Retrieved RAG results count=%s sensor_uuid=%s", len(results), sensor_uuid)
@@ -109,11 +130,12 @@ def build_rag_context(
 
 def chat_rag_stream(
     query: str,
-    sensor_uuid: str,
+    sensor_uuid: str | None = None,
     config: RAGConfig | None = None,
     limit: int = 5,
     system_override: str | None = None,
     kb_name: str | None = None,
+    service_id: str | None = None,
 ):
     logger.info(
         "chat_rag_stream started sensor_uuid=%s kb_name=%s limit=%s query_len=%s",
@@ -137,24 +159,43 @@ def chat_rag_stream(
         تک‌تک deltaهای content به‌صورت رشته
     """
     cfg = config or load_rag_config()
-    client = get_chat_client(cfg)
-    model = cfg.llm.model
-    logger.debug("Loaded RAG config with model=%s", model)
+    resolved_service_id = service_id or kb_name or _detect_kb_intent(query)
+    service = get_service_config(resolved_service_id, cfg)
+    service_llm_config = service.llm
+    service_cfg = RAGConfig(
+        embedding=cfg.embedding,
+        qdrant=cfg.qdrant,
+        chunking=cfg.chunking,
+        llm=service_llm_config,
+        knowledge_bases=cfg.knowledge_bases,
+        services=cfg.services,
+        chromadb=cfg.chromadb,
+    )
+    client = get_chat_client(service_cfg)
+    model = service_llm_config.model
+    logger.debug("Loaded service config service_id=%s model=%s", resolved_service_id, model)
 
-    detected_kb = kb_name or _detect_kb_intent(query)
-    logger.info("Using knowledge base=%s", detected_kb)
+    detected_kb = kb_name or service.knowledge_base
+    logger.info("Using knowledge base=%s for service_id=%s", detected_kb, resolved_service_id)
     context = build_rag_context(
-        query, sensor_uuid, config=cfg, limit=limit, kb_name=detected_kb,
+        query,
+        sensor_uuid,
+        config=cfg,
+        limit=limit,
+        kb_name=detected_kb,
+        service_id=resolved_service_id,
     )
     logger.debug("Built context length=%s", len(context))
 
     if system_override is not None:
         system_content = system_override
     else:
-        tone = _load_kb_tone(detected_kb, cfg)
+        tone = _load_service_tone(service, cfg)
         if not tone:
             tone = _load_tone(cfg)
         system_parts = [tone] if tone else []
+        if service.system_prompt:
+            system_parts.append(service.system_prompt)
         system_parts.append(
             "با استفاده از بخش «داده‌های فعلی خاک شما» و «متن‌های مرجع» زیر به سوال کاربر پاسخ بده. "
             "برای سوالاتی درباره خاک کاربر (مثل pH، رطوبت، NPK) حتماً از داده‌های فعلی استفاده کن. "
@@ -169,7 +210,7 @@ def chat_rag_stream(
         {"role": "system", "content": system_content},
         {"role": "user", "content": query},
     ]
-    logger.info("Prepared messages for model=%s  message=%s", model,messages)
+    logger.info("Prepared messages for model=%s service_id=%s", model, resolved_service_id)
 
     stream = client.chat.completions.create(
         model=model,