API Generating Language Model: Difference between revisions

From GM-RKB
Jump to navigation Jump to search
No edit summary
m (Text replacement - "** ..." to "** …")
Line 6: Line 6:
** It is evaluated using AST matching against reference APIs.
** It is evaluated using AST matching against reference APIs.
** It is optimized for invoking APIs as tools.
** It is optimized for invoking APIs as tools.
** ...
**
* <B>Example(s):</B>
* <B>Example(s):</B>
** [[Gorilla LLM]] ().
** [[Gorilla LLM]] ().
** [[Anthropic's Claude]] can produce API calls for a variety of provided APIs.
** [[Anthropic's Claude]] can produce API calls for a variety of provided APIs.
** [[Toolformer LLM]].
** [[Toolformer LLM]].
** ...
**
* <B>Counter-Example(s):</B>
* <B>Counter-Example(s):</B>
** A [[Chatbot LLM]] is not optimized for API generation.
** A [[Chatbot LLM]] is not optimized for API generation.
** An [[LLM for Mathematical Reasoning]] focuses on math not coding.
** An [[LLM for Mathematical Reasoning]] focuses on math not coding.
** ...
**
* <B>See:</B> [[API Call]], [[LLM for Programming]], [[Code Generation]].
* <B>See:</B> [[API Call]], [[LLM for Programming]], [[Code Generation]].
----
----
----
----
[[Category:Concept]]
[[Category:Concept]]

Revision as of 07:07, 8 November 2023

A API Generating Language Model is a software-generating language model specialized for generating API calls from natural language instructions.

  • Context:
    • It can be trained on API documentation and associated natural language descriptions.
    • It takes a specification and outputs an API call with the right components filled in.
    • It focuses on producing valid API calls over full programs.
    • It is evaluated using AST matching against reference APIs.
    • It is optimized for invoking APIs as tools.
  • Example(s):
  • Counter-Example(s):
  • See: API Call, LLM for Programming, Code Generation.