LLMs
Empower AI assistants with trained, unstructured dialogue.
The types of training resources and frequency depends on the subscription plan.
Third-party LLMs from providers like OpenAI and Anthropic can be integrated into an AI assistant, supporting its broader chat flow.
Go to the AI Assistant dashboard's LLM tab for configuration options.
Manage an LLM
Configure these top-level options:
Fallback to GPT-4o — toggles the LLM integration on or off.
Personalisation Prompt — text that gets applied alongside the person's chat message to every LLM input. This allows you to define the LLM's persona, personality, tone of voice, behaviour, instructions, rules, etc.
Press Save to confirm edits.
AI assistants currently use OpenAI's 4o model by default.
Model selection will be rolling out shortly.
Add training
While triggers and actions add structure to the chat flow, LLMs serve as a catch-all fallback and provide unstructured responses. This organic conversation is powerful and intuitive, but only useful if the LLM provides accurate, domain-specific answers to your audience's questions. Training the LLM accomplishes this, which multiple training options available:
Upload File
Select Upload File.
Insert a file name, or skip for auto-naming.
Select Browse Files or drag-and-drop a file. CSV, JSON, and PDF files up to 5MB are accepted.
Press Train to confirm upload.
Add URL
Select Add URL.
Give the URL resource a Name.
Insert a valid URL of the web address the LLM will scrape from.
Enable proxy bypass if the website is behind a proxy or firewall.
Set the crawling method:
All Pages — will scrape from the URL page and every sub-page.
Specific Pages — will only scrape from pages not omitted by the Excluded Pages input, where pages to exclude get listed, one per line. Use * as a wildcard slug to exclude all pages paths in that position. For example, https://acme.com/pricing/* will omit every page located at /pricing/[page].
Toggle Automatically retrain every [frequency] to enable/disable retraining. Available frequencies, depending on subscription plan, are:
1 hour
12 hours
1 day
1 week
Press Train to confirm.
Paste Snippet
Snippets are raw text you can type or paste as an alternative to adding files or URLs.
Select Paste Snippet.
Give the snippet a Name.
Insert the Text snippet, which the LLM will refer to as needed.
Press Train to save.
Existing training
The Existing Training table displays all resources that have been added. The Status field indicates the current context:
Pending — resource is being processed.
Success — resource is actively available to the LLM when needed.
Failure — resource failed to import.
The table can be searched or filtered, and each resource row can be selected for additional info.
Delete training
In the table, select one or more resource checkbox. Press Delete Content and confirm.
Last updated