phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: Fix docs lint issues (#1993)

Browse source 
# What does this PR do?

This was not caught as part of the CI build:
dd62a2388c.
[This PR](https://github.com/meta-llama/llama-stack/pull/1354) was too
old and didn't include the additional CI builds yet.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-04-18 02:33:13 -04:00 • committed by GitHub
parent dd62a2388c
commit 4c6b7005fa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 15 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

26
docs/source/building_applications/tools.md
View file

@ -215,7 +215,7 @@ response = agent.create_turn(
)
```
## Simple Example 2: Using an Agent with the Web Search Tool
1. Start by registering a Tavily API key at [Tavily](https://tavily.com/).
1. Start by registering a Tavily API key at [Tavily](https://tavily.com/).
2. [Optional] Provide the API key directly to the Llama Stack server
```bash
export TAVILY_SEARCH_API_KEY="your key"
@ -232,22 +232,26 @@ from llama_stack_client import LlamaStackClient
client = LlamaStackClient(
base_url=f"http://localhost:8321",
provider_data = {"tavily_search_api_key": "your_TAVILY_SEARCH_API_KEY"} # Set this from the client side. No need to provide it if it has already been configured on the Llama Stack server.
)
provider_data={
"tavily_search_api_key": "your_TAVILY_SEARCH_API_KEY"
}, # Set this from the client side. No need to provide it if it has already been configured on the Llama Stack server.
)
agent = Agent(
client,
client,
model="meta-llama/Llama-3.2-3B-Instruct",
instructions=(
"You are a web search assistant, must use websearch tool to look up the most current and precise information available. "
),
tools=["builtin::websearch"],
)
tools=["builtin::websearch"],
)
session_id = agent.create_session("websearch-session")
response = agent.create_turn(
messages=[{"role": "user", "content": "How did the USA perform in the last Olympics?"}],
messages=[
{"role": "user", "content": "How did the USA perform in the last Olympics?"}
],
session_id=session_id,
)
for log in EventLogger().log(response):
@ -264,15 +268,15 @@ for log in EventLogger().log(response):
```python
client = LlamaStackClient(
base_url="http://localhost:8321",
provider_data={"wolfram_alpha_api_key": wolfram_api_key}
provider_data={"wolfram_alpha_api_key": wolfram_api_key},
)
```
3. Configure the tools in the Agent by setting `tools=["builtin::wolfram_alpha"]`.
4. Example user query:
```python
response = agent.create_turn(
messages=[{"role": "user", "content": "Solve x^2 + 2x + 1 = 0 using WolframAlpha"}],
session_id=session_id,
messages=[{"role": "user", "content": "Solve x^2 + 2x + 1 = 0 using WolframAlpha"}],
session_id=session_id,
)
```
```
```