first commit

rag/config.py

@@ -1,5 +1,5 @@
 """
-بارگذاری تنظیمات RAG از rag_config.yaml
+بارگذاری تنظیمات RAG از rag_config.yaml — با پشتیبانی از چند provider و چند پایگاه دانش
 """
 import os
 from dataclasses import dataclass, field
@@ -16,6 +16,8 @@ class EmbeddingConfig:
     batch_size: int = 32
     api_key_env: str | None = None
     base_url: str | None = None
+    avalai_base_url: str | None = None
+    avalai_api_key_env: str | None = None
 
 
 @dataclass
@@ -37,6 +39,15 @@ class LLMConfig:
     model: str = "gpt-4o"
     base_url: str | None = None
     api_key_env: str | None = None
+    avalai_base_url: str | None = None
+    avalai_api_key_env: str | None = None
+
+
+@dataclass
+class KnowledgeBaseConfig:
+    path: str
+    tone_file: str
+    description: str = ""
 
 
 @dataclass
@@ -45,8 +56,7 @@ class RAGConfig:
     qdrant: QdrantConfig
     chunking: ChunkingConfig
     llm: LLMConfig = field(default_factory=LLMConfig)
-    tone_file: str = "config/tone.txt"
-    knowledge_base_path: str = "config/knowledge_base"
+    knowledge_bases: dict[str, KnowledgeBaseConfig] = field(default_factory=dict)
     chromadb: dict[str, Any] = field(default_factory=dict)
 
 
@@ -73,6 +83,8 @@ def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
         batch_size=emb.get("batch_size", 32),
         api_key_env=emb.get("api_key_env"),
         base_url=emb.get("base_url"),
+        avalai_base_url=emb.get("avalai_base_url"),
+        avalai_api_key_env=emb.get("avalai_api_key_env"),
     )
 
     qd = data.get("qdrant", {})
@@ -94,14 +106,24 @@ def load_rag_config(config_path: str | Path | None = None) -> RAGConfig:
         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"),
     )
 
+    kb_data = data.get("knowledge_bases", {})
+    knowledge_bases: dict[str, KnowledgeBaseConfig] = {}
+    for kb_name, kb_conf in kb_data.items():
+        knowledge_bases[kb_name] = KnowledgeBaseConfig(
+            path=kb_conf.get("path", f"config/knowledge_base/{kb_name}"),
+            tone_file=kb_conf.get("tone_file", f"config/tones/{kb_name}_tone.txt"),
+            description=kb_conf.get("description", ""),
+        )
+
     return RAGConfig(
         embedding=embedding,
         qdrant=qdrant,
         chunking=chunking,
         llm=llm,
-        tone_file=data.get("tone_file", "config/tone.txt"),
-        knowledge_base_path=data.get("knowledge_base_path", "config/knowledge_base"),
+        knowledge_bases=knowledge_bases,
         chromadb=data.get("chromadb", {}),
     )