Spaces:
Paused
Advanced overview of the "dynamic prompts" function
Hello HuggingChat,
I have studied the results of the web search for information on the "dynamic prompts" function and found only a brief description, apparently based on the context contained in the footnote: "Allow the use of template variables {{url=https://example.com/path}} to insert dynamic content into your prompt by making GET requests to specified URLs on each inference."
This is a very superficial representation of the described functionality. Sometimes "AI assistants" behave illogically when you try to use certain "HuggingChat" functions.
Could you provide an extended representation of this function:
- Detailed description of the mechanism of the "dynamic prompts" function.
- Examples of using "dynamic prompts" in various scenarios to better understand its practical application.
- Recommendations for the effective use of this function, including information on possible limitations.
Providing such extended information will help make more rational decisions when working with "dynamic prompts" and avoid misunderstanding or unexpected behavior of the AI assistant.
I would be grateful if you could provide a more detailed description of this functionality. This will allow a better understanding of its capabilities and use them with maximum efficiency.
Agree, I asked myself same question
After reading the code https://github.com/huggingface/chat-ui/blob/18fba9f7bbcd73c9a9c39b1cbfbabf5fa50767ed/src/routes/conversation/%5Bid%5D/%2Bserver.ts#L385
I succeed to play with it.
Let say system prompt is
You are a helpful assistant
You received this instruction from dynamic request as a json:
{{url=https://example.com/api/instruction}}
Let say https://example.com/api/instruction will returns this json
{"instruction":"say hello"}
Now if user say "proceed" in the chat, system prompt will be dynamically updated to
You are a helpful assistant
You received this instruction from dynamic request as a json:
{"instruction":"say hello"}
And inference will start
Yes I think we'll document this feature a bit better when we have time.