apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-05 14:45:15 +02:00
Code Issues Projects Releases Packages Wiki Activity

Use intent model from archfc to pick prompt gateway (#328)

Browse source
This commit is contained in:
Shuguang Chen 2024-12-20 13:25:01 -08:00 • committed by GitHub
parent 67b8fd635e
commit ba7279becb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
151 changed files with 8642 additions and 10932 deletions
Download patch file Download diff file Expand all files Collapse all files

22
docs/source/build_with_arch/agent.rst
View file

@ -1,18 +1,18 @@
.. _arch_agent_guide:
Agentic Workflow
==============================
Agentic Apps
=============
Arch helps you easily personalize your applications by calling application-specific (API) functions
via user prompts. This involves any predefined functions or APIs you want to expose to users to perform tasks,
gather information, or manipulate data. This capability is generally referred to as :ref:`function calling <function_calling>`, where
you have the flexibility to support “agentic” apps tailored to specific use cases - from updating insurance
claims to creating ad campaigns - via prompts.
Arch helps you build personalized agentic applications by calling application-specific (API) functions via user prompts.
This involves any predefined functions or APIs you want to expose to users to perform tasks, gather information,
or manipulate data. This capability is generally referred to as :ref:`function calling <function_calling>`, where
you can support “agentic” apps tailored to specific use cases - from updating insurance claims to creating ad campaigns - via prompts.
Arch analyzes prompts, extracts critical information from prompts, engages in lightweight conversation with
the user to gather any missing parameters and makes API calls so that you can focus on writing business logic.
Arch does this via its purpose-built `Arch-Function <https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68>`_ - the fastest (200ms p90 - 10x faser than GPT-4o)
and cheapest (100x than GPT-4o) function calling LLM that matches performance with frontier models.
Arch analyzes prompts, extracts critical information from prompts, engages in lightweight conversation with the user to
gather any missing parameters and makes API calls so that you can focus on writing business logic. Arch does this via its
purpose-built `Arch-Function <https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68>`_ -
the fastest (200ms p50 - 12x faser than GPT-4o) and cheapest (44x than GPT-4o) function calling LLM that matches or outperforms
frontier LLMs.
.. image:: includes/agent/function-calling-flow.jpg
:width: 100%