still not able to train may model (excpet if I set flow_retrieval to False but I want ti use Entreprise search functionnalities)
Give Feedback / Get Help: Sign in to GitHub · GitHub LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True’.
Provider List: Providers | liteLLM
Provider List: Providers | liteLLM
2025-03-28 17:00:44 ERROR rasa.dialogue_understanding.generator.flow_retrieval - [error ] Failed to populate the FAISS store with the provided flows. error=ProviderClientAPIException(‘Failed to embed documents\nOriginal error: litellm.APIConnectionError: OllamaException - Connection error.)’) error_type=ProviderClientAPIException event_key=flow_retrieval.populate_vector_store.not_populated 2025-03-28 17:00:44 ERROR rasa.dialogue_understanding.generator.llm_based_command_generator - [error ] Flow retrieval store is inaccessible. error=ProviderClientAPIException(‘Failed to embed documents\nOriginal error: litellm.APIConnectionError: OllamaException - Connection error.)’) event_key=llm_based_command_generator.train.failed 2025-03-28 17:00:44 ERROR rasa.engine.graph - [error ] graph.node.error_running_component node_name=train_CompactLLMCommandGenerator0 2025-03-28 17:00:44 ERROR rasa.main - [error ] ProviderClientAPIException: Failed to embed documents Original error: litellm.APIConnectionError: OllamaException - Connection error. event_key=cli.exception.rasa_exception
my current config, following rasa CALM docs and Rasa CAML forum
config.yml
recipe: default.v1 language: en pipeline:
- name: CompactLLMCommandGenerator llm: model_group: ollama-gemma3-1b flow_retrieval: embeddings: model_group: text_embedding_model policies:
- name: RulePolicy # Remplace FlowPolicy si problème
- name: MemoizationPolicy assistant_id: 20250328-161232-caramelized-continent
endpoints.yml
action_endpoint: actions_module: “actions”
model_groups:
- id: ollama-gemma3-1b models:
- provider: ollama api_base: “http://localhost:11434” model: gemma3:1b
- id: text_embedding_model models:
- provider: ollama api_base: “http://localhost:11434” model: text-embedding-ada-002