- 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_api/__init__.py

@@ -15,6 +15,7 @@ from common.utils.database import Database
 from config.logging_config import LOGGING
 from .api.document_api import document_ns
 from .api.auth import auth_ns
+from .api.specialist_execution_api import specialist_execution_ns
 from config.config import get_config
 from common.utils.celery_utils import make_celery, init_celery
 from common.utils.eveai_exceptions import EveAIException
@@ -127,7 +128,7 @@ def register_extensions(app):
             "expose_headers": ["Content-Length", "Content-Range"],
             "supports_credentials": True,
             "max_age": 1728000,  # 20 days
-            "allow_credentials": True
+            # "allow_credentials": True
         }
     })
 
@@ -135,6 +136,7 @@ def register_extensions(app):
 def register_namespaces(app):
     api_rest.add_namespace(document_ns, path='/api/v1/documents')
     api_rest.add_namespace(auth_ns, path='/api/v1/auth')
+    api_rest.add_namespace(specialist_execution_ns, path='/api/v1/specialist-execution')
 
 
 def register_blueprints(app):