All - Activity - Shashanka - Rasa Community Forum

Local LLM and Embedding Configuration Issues in Rasa Pro

I’m not using docker. The errors I had received were because of the embedding model and flow retrieval related.

Whether it can predict the actions and flow steps with your current config file?

Hey Sanjukta. Whether you were successful connecting the local LLM at least? I was not able to do that. Can you share your configurations files please and the method through which you are launching the LLM server?

Hey @Balowen, My bot is using the following components.
LLMCommandGenerator, FlowPolicy, IntentlessPolicy, EnterpriseSearchPolicy, rasa.core.ContextualResponseRephraser. Could you tell me which of these require LLM configuration and which of these demand Embedding configuration? I have been trying ev…

Hello Omar,
Thank you for reaching out. Currently, I am still in the process of learning and exploring Rasa myself, so I wouldn’t be able to do that. Best of luck with your search and studies!

Hey @Balowen,
Thank you for your response. I will try and get back to you about this. Meanwhile, could you please let me know the embedding provider that you are using? If possible, please do share the config and endpoint configuration here. Many thanks in advance.

Hey Lewis. Please help me out with my issue related to Ollama and Rasa Pro CALM integration as it seems you were able to integrate Ollama with RASA Pro Calm perfectly. I’m sharing the link to my issue. If possible, please do share your config and endpoints setup. Any help is highly appreciated.

Hello Community!!
I have a perfectly working RASA Pro CALM (v3.8.7) chatbot which is dependent on OpenAI for tasks such as ‘Enterprise Search Policy’, ‘Intentless Policy’, ‘Command Generator’, ‘Contextual Response Rephraser’ etc. Now that I need to make the chatbot completely independent, I need to…

I’m trying out Rasa_Pro developer edition. During the flow, I’m setting a few of the slots within the flow. A small example section is given below.
next: