Spaces:

NextDrought
/

mcp-server

Sleeping

burtenshaw commited on May 16, 2025

Commit

c7998ab

unverified ·

2 Parent(s): ef13ca3 e0273a7

Merge pull request #9 from ismael-dm/remove-extra-note

Files changed (1) hide show

units/en/unit2/tiny-agents.mdx CHANGED Viewed

@@ -130,7 +130,6 @@ The canonical documentation I will link to here is [OpenAI's function calling do
 Inference engines let you pass a list of tools when calling the LLM, and the LLM is free to call zero, one or more of those tools.
 As a developer, you run the tools and feed their result back into the LLM to continue the generation.
-> [!NOTE]
 > Note that in the backend (at the inference engine level), the tools are simply passed to the model in a specially-formatted `chat_template`, like any other message, and then parsed out of the response (using model-specific special tokens) to expose them as tool calls.
 ## Implementing an MCP client on top of InferenceClient

 Inference engines let you pass a list of tools when calling the LLM, and the LLM is free to call zero, one or more of those tools.
 As a developer, you run the tools and feed their result back into the LLM to continue the generation.
 > Note that in the backend (at the inference engine level), the tools are simply passed to the model in a specially-formatted `chat_template`, like any other message, and then parsed out of the response (using model-specific special tokens) to expose them as tool calls.
 ## Implementing an MCP client on top of InferenceClient