- Implementation of specialist execution api, including SSE protocol

- eveai_chat becomes deprecated and should be replaced with SSE
- Adaptation of STANDARD_RAG specialist
- Base class definition allowing to realise specialists with crewai framework
- Implementation of SPIN_SPECIALIST
- Implementation of test app for testing specialists (test_specialist_client). Also serves as an example for future SSE-based client
- Improvements to startup scripts to better handle and scale multiple connections
- Small improvements to the interaction forms and views
- Caching implementation improved and augmented with additional caches

eveai_chat_workers/retrievers/retriever_typing.py

@@ -1,6 +1,9 @@
 from typing import Dict, Any
+
+from flask import current_app
 from pydantic import BaseModel, Field, model_validator
-from config.type_defs.retriever_types import RETRIEVER_TYPES
+from common.extensions import cache_manager
+
 
 
 class RetrieverMetadata(BaseModel):
@@ -28,6 +31,7 @@ class RetrieverArguments(BaseModel):
     based on RETRIEVER_TYPES configuration.
     """
     type: str = Field(..., description="Type of retriever (e.g. STANDARD_RAG)")
+    type_version: str = Field(..., description="Version of retriever type (e.g. 1.0)")
 
     # Allow any additional fields
     model_config = {
@@ -37,7 +41,7 @@ class RetrieverArguments(BaseModel):
     @model_validator(mode='after')
     def validate_required_arguments(self) -> 'RetrieverArguments':
         """Validate that all required arguments for this retriever type are present"""
-        retriever_config = RETRIEVER_TYPES.get(self.type)
+        retriever_config = cache_manager.retrievers_config_cache.get_config(self.type, self.type_version)
         if not retriever_config:
             raise ValueError(f"Unknown retriever type: {self.type}")