Create a chatbot profile - Fluid Topics - Latest

Use Chatbot profiles for the Chatbot component. They differ from Completion profiles because they remember previous calls and answers.

To create a Chatbot profile go through the following steps:

1. Select New profile.

2. Select Chatbot.

3. Enter or select:

   • A name.

     Generative ID profile names and IDs must be different from existing profiles.

   • A unique profile ID.

   • A provider: choose one of Amazon Bedrock, Anthropic, Azure, Fluid Topics, Google, MyLLM, or OpenAI.

     The MyLLM option makes it possible to provide the URL to an LLM deployment, making it possible to integrate self-hosted models with Fluid Topics. The LLM model must be compliant with the OpenAI API specification.

     With Fluid Topics models, the content of documents and user conversations is not accessible to an external provider.

   • An LLM model from the selected provider.

     • A host and model name for Azure and MyLLM.
     • The LLM model dropdown menu is not exhaustive. It is possible to enter any value, as long as it matches a valid model from the selected LLM provider. For example, in the case of a refined model only known by the person configuring the profile.
     • Use the Test connection button to check the profile configuration.

   • An API key from the provider.

   • Chatbot instructions.

     !!! info"" - The chatbot prompt defines specific instructions and the conversation scope for the bot. - For more information, see the Advanced settings for Chatbot profiles topic.

4. Select Save.

Once created, ADMIN users can copy the chatbot profile ID to use in generative AI features.

Chatbot generative AI features include:

• The Chatbot component
• The Retrieval-augmented generation (RAG) web service.