Configurations

Your GPT configuration includes various settings for your GPT-AI, such as the LLM to use and its persona.

Configuration persona and language settings

Persona

Your GPT persona is a way to give your bot instructions on who it is and how it should behave.

• Bot's name and purpose

• Your organisation's name and a short description

• How the bot should write its answer

• Specific behaviour: "If asked about X answer Y"

For more information on how to use the persona click here.

Language

This setting will prompt the bot to speak a specific language. Same as bot - The language set when the bot was created Same as user - The bot imitates the language of the user Custom language - Manually set a language

Prompt version

v1: Text answers & human handover

Use this setting if the system should only provide text answers based on the uploaded knowledge base or transfer the conversation to a human agent.

v2: Integrated tool calling

This setting enables the system to utilize any of the native AI tools available in the configuration.

v3: Updated tool calling prompt with matching template (recommended)

Similar to v2, this is a tool-calling prompt updated to align with the new persona template. This version resolves contradictions found in v2 and removes redundant instructions that are already covered by the new template.

Custom prompt

With this setting you're in full control of the LLMs instructions, use this setting if you for example want the LLM to be able to discuss topics beyond the information in the uploaded knowledge base. The LLM will still receive the following information:

• Your uploaded documents in the selected dataset.

• The current time, provided as a timestamp

Data set

Select what data set the bot should use as a source for it answer

Source Retrieval Settings

Create a custom setup for how the Embedder should find sources. For most use cases the default setting is good enough. Above is the default setting of how sources are retrieved.

Retrieving significantly more sources than the default setting can slow down answer generation. Additionally, EGPT models have built-in limits on how many sources they can process, so even if you retrieve 30 sources, the model may not be able to read them all.

GPT LLM

Ebbot GPT - Select if you want to use one of Ebbot's LLM hosted on EU servers by EU companies and fine tuned for customer service.

OpenAI GPT (Azure) - Use OpenAI's model hosted through Microsoft Azure.

Google AI - Access Google's Gemini models through their API.

GPT LLM versions

We regularly release new LLM versions that are smarter, faster, cheaper, or include new functionality. The latest model isn't necessarily the best for your use case. Click on EGPT LLMs below to read more about the current models.

EbbotGPT LLMs

Safe Guards

Use our safeguards to block malicious attempts to generate irrelevant or harmful content.

Safe Guards

Tools

If you have selected prompt version: v2 you will be able to select AI tools that your AI agent has access to.

AI tools

Advanced

Configuration advanced settings

Number of messages in GPT memory - How many messages in the chat history should the GPT model use as a basis for its answer. Changing the following settings usually has a minimal impact on the bot's answers. While adjustments can positively affect specific questions, they might negatively impact others. Use with caution.

Temperature - Recommended setting 0.1

Top P - Recommended setting 0.1

Typ P - Recommended setting 0.5

Top K - Recommeded setting 40