AI UPDATE

rag/config.py

@@ -1,5 +1,6 @@
 """
-بارگذاری تنظیمات RAG از rag_config.yaml — با پشتیبانی از چند provider و چند پایگاه دانش
+بارگذاری تنظیمات RAG از rag_config.yaml — با پشتیبانی از چند provider،
+چند پایگاه دانش و چند سرویس.
 """
 import os
 from dataclasses import dataclass, field
@@ -36,6 +37,7 @@ class ChunkingConfig:
 
 @dataclass
 class LLMConfig:
+    provider: str = "gapgpt"
     model: str = "gpt-4o"
     base_url: str | None = None
     api_key_env: str | None = None
@@ -50,6 +52,17 @@ class KnowledgeBaseConfig:
     description: str = ""
 
 
+@dataclass
+class ServiceConfig:
+    service_id: str
+    knowledge_base: str
+    llm: LLMConfig = field(default_factory=LLMConfig)
+    tone_file: str | None = None
+    system_prompt: str | None = None
+    use_user_embeddings: bool = True
+    description: str = ""
+
+
 @dataclass
 class RAGConfig:
     embedding: EmbeddingConfig
@@ -57,9 +70,31 @@ class RAGConfig:
     chunking: ChunkingConfig
     llm: LLMConfig = field(default_factory=LLMConfig)
     knowledge_bases: dict[str, KnowledgeBaseConfig] = field(default_factory=dict)
+    services: dict[str, ServiceConfig] = field(default_factory=dict)
     chromadb: dict[str, Any] = field(default_factory=dict)
 
 
+def _build_llm_config(data: dict[str, Any] | None, default: LLMConfig | None = None) -> LLMConfig:
+    llm_data = data or {}
+    fallback = default or LLMConfig()
+    return LLMConfig(
+        provider=llm_data.get("provider", fallback.provider),
+        model=llm_data.get("model", fallback.model),
+        base_url=llm_data.get("base_url", fallback.base_url),
+        api_key_env=llm_data.get("api_key_env", fallback.api_key_env),
+        avalai_base_url=llm_data.get("avalai_base_url", fallback.avalai_base_url),
+        avalai_api_key_env=llm_data.get("avalai_api_key_env", fallback.avalai_api_key_env),
+    )
+
+
+def get_service_config(service_id: str, config: RAGConfig | None = None) -> ServiceConfig:
+    cfg = config or load_rag_config()
+    service = cfg.services.get(service_id)
+    if service is None:
+        raise KeyError(f"Unknown service_id: {service_id}")
+    return service
+
+
 def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
     """
     بارگذاری تنظیمات از YAML و env.
@@ -101,14 +136,7 @@ def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
         overlap_tokens=ch.get("overlap_tokens", 50),
     )
 
-    llm_data = data.get("llm", {})
-    llm = LLMConfig(
-        model=llm_data.get("model", "gpt-4o"),
-        base_url=llm_data.get("base_url"),
-        api_key_env=llm_data.get("api_key_env"),
-        avalai_base_url=llm_data.get("avalai_base_url"),
-        avalai_api_key_env=llm_data.get("avalai_api_key_env"),
-    )
+    llm = _build_llm_config(data.get("llm", {}))
 
     kb_data = data.get("knowledge_bases", {})
     knowledge_bases: dict[str, KnowledgeBaseConfig] = {}
@@ -119,11 +147,38 @@ def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
             description=kb_conf.get("description", ""),
         )
 
+    services_data = data.get("services", {})
+    services: dict[str, ServiceConfig] = {}
+    for service_id, service_conf in services_data.items():
+        kb_name = service_conf.get("knowledge_base", service_id)
+        kb_conf = knowledge_bases.get(kb_name)
+        services[service_id] = ServiceConfig(
+            service_id=service_id,
+            knowledge_base=kb_name,
+            llm=_build_llm_config(service_conf.get("llm"), default=llm),
+            tone_file=service_conf.get("tone_file") or (kb_conf.tone_file if kb_conf else None),
+            system_prompt=service_conf.get("system_prompt"),
+            use_user_embeddings=service_conf.get("use_user_embeddings", True),
+            description=service_conf.get("description", ""),
+        )
+
+    if not services:
+        for kb_name, kb_conf in knowledge_bases.items():
+            services[kb_name] = ServiceConfig(
+                service_id=kb_name,
+                knowledge_base=kb_name,
+                llm=llm,
+                tone_file=kb_conf.tone_file,
+                use_user_embeddings=True,
+                description=kb_conf.description,
+            )
+
     return RAGConfig(
         embedding=embedding,
         qdrant=qdrant,
         chunking=chunking,
         llm=llm,
         knowledge_bases=knowledge_bases,
+        services=services,
         chromadb=data.get("chromadb", {}),
     )