phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions
llama-stack/docs
History
Xi Yan 0fe071764f
feat(1/n): api: unify agents for handling server & client tools (#1178) 
# Problem

Our current Agent framework has discrepancies in definition on how we
handle server side and client side tools.

1. Server Tools: a single Turn is returned including `ToolExecutionStep`
in agenst
2. Client Tools: `create_agent_turn` is called in loop with client agent
lib yielding the agent chunk

ad6ffc63df/src/llama_stack_client/lib/agents/agent.py (L186-L211)

This makes it inconsistent to work with server & client tools. It also
complicates the logs to telemetry to get information about agents turn /
history for observability.

#### Principle
The same `turn_id` should be used to represent the steps required to
complete a user message including client tools.

## Solution

1. `AgentTurnResponseEventType.turn_awaiting_input` status to indicate
that the current turn is not completed, and awaiting tool input
2. `continue_agent_turn` endpoint to update agent turn with client's
tool response.


# What does this PR do?
- Skeleton API as example

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]

- Just API update, no functionality change
```
llama stack run + client-sdk test
```

<img width="842" alt="image"
src="https://github.com/user-attachments/assets/7ac56b5f-f424-4632-9476-7e0f57555bc3"
/>


[//]: # (## Documentation)
2025-02-21 11:48:27 -08:00
..
_static feat(1/n): api: unify agents for handling server & client tools (#1178) 2025-02-21 11:48:27 -08:00
notebooks chore!: deprecate eval/tasks (#1186) 2025-02-20 14:06:21 -08:00
openapi_generator fix: some telemetry APIs don't currently work (#1188) 2025-02-20 14:09:25 -08:00
resources Several documentation fixes and fix link to API reference 2025-02-04 14:00:43 -08:00
source chore: move embedding deps to RAG tool where they are needed (#1210) 2025-02-21 11:33:41 -08:00
zero_to_hero_guide rename 2025-02-18 16:02:44 -08:00
conftest.py No spaces in ipynb tests 2025-02-07 11:56:22 -08:00
contbuild.sh Fix broken links with docs 2024-11-22 20:42:17 -08:00
dog.jpg Support for Llama3.2 models and Swift SDK (#98) 2024-09-25 10:29:58 -07:00
getting_started.ipynb fix notebook 2025-02-13 16:52:46 -08:00
license_header.txt Initial commit 2024-07-23 08:32:33 -07:00
make.bat first version of readthedocs (#278) 2024-10-22 10:15:58 +05:30
Makefile first version of readthedocs (#278) 2024-10-22 10:15:58 +05:30
readme.md Fix README.md notebook links (#976) 2025-02-05 14:33:46 -08:00
requirements.txt Pin sphinx 2025-02-19 20:20:46 -08:00

readme.md

Llama Stack Documentation

Here's a collection of comprehensive guides, examples, and resources for building AI applications with Llama Stack. For the complete documentation, visit our ReadTheDocs page.

Content

Try out Llama Stack's capabilities through our detailed Jupyter notebooks: