Commit graph

10 commits

Author SHA1 Message Date
Reid
89d37687dd
chore: remove --no-list-templates option (#1121)
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]

From the code and the usage, seems cannot see that need to use
`--no-list-templates` to handle, and also make the user confused from
the help text, so try to remove it.
```
$ llama stack build --no-list-templates
> Enter a name for your Llama Stack (e.g. my-local-stack):

$ llama stack build
> Enter a name for your Llama Stack (e.g. my-local-stack):

before:
$ llama stack build --help
  --list-templates, --no-list-templates
                        Show the available templates for building a Llama Stack distribution (default: False)

after:
  --list-templates      Show the available templates for building a Llama Stack distribution
```

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## 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.*]

[//]: # (## Documentation)

Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
2025-02-18 10:13:46 -08:00
Charlie Doern
025f615868
feat: add support for running in a venv (#1018)
# What does this PR do?

add --image-type to `llama stack run`. Which takes conda, container or
venv also add start_venv.sh which start the stack using a venv

resolves #1007

## Test Plan

running locally:

`llama stack build --template ollama --image-type venv`
`llama stack run --image-type venv
~/.llama/distributions/ollama/ollama-run.yaml`
...
```
llama stack run --image-type venv ~/.llama/distributions/ollama/ollama-run.yaml
Using run configuration: /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml
+ python -m llama_stack.distribution.server.server --yaml-config /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml --port 8321
Using config file: /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml
Run configuration:
apis:
- agents
- datasetio
...
```

Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-02-12 11:13:04 -05:00
Hardik Shah
74e933cbfd
More Updates to Read the Docs (#856) 2025-01-23 11:39:33 -08:00
Hardik Shah
25a70ca4dc
Fixed distro documentation (#852)
More docs
2025-01-23 08:19:51 -08:00
Yuan Tang
6da3053c0e
More generic image type for OCI-compliant container technologies (#802)
It's a more generic term and applicable to alternatives of Docker, such
as Podman or other OCI-compliant technologies.

---------

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-01-17 16:37:42 -08:00
Ashwin Bharambe
03ac84a829 Update default port from 5000 -> 8321 2025-01-16 15:26:48 -08:00
Yuan Tang
eee25db11d
Add missing "inline::" prefix for providers in building_distro.md (#702)
This fixes the following errors:

```
ValueError: Provider `meta-reference` is not available for API `agents`
ValueError: Provider `meta-reference` is not available for API `telemetry`
```
2025-01-02 09:03:30 -08:00
Henry Tu
64c6df8392
Cerebras Inference Integration (#265)
Adding Cerebras Inference as an API provider.

## Testing

### Conda
```
$ llama stack build --template cerebras --image-type conda
$ llama stack run ~/.llama/distributions/llamastack-cerebras/cerebras-run.yaml
...
Listening on ['::', '0.0.0.0']:5000
INFO:     Started server process [12443]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://['::', '0.0.0.0']:5000 (Press CTRL+C to quit)
```

### Chat Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/chat-completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": "What is the temperature in Seattle right now?"
        }
    ],
    "stream": false,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 100
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}' 
```

#### Non-Streaming Response
```
{
  "completion_message": {
    "role": "assistant",
    "content": "",
    "stop_reason": "end_of_message",
    "tool_calls": [
      {
        "call_id": "6f42fdcc-6cbb-46ad-a17b-5d20ac64b678",
        "tool_name": "getTemperature",
        "arguments": {
          "location": "Seattle"
        }
      }
    ]
  },
  "logprobs": null
}
```

#### Streaming Response
```
data: {"event":{"event_type":"start","delta":"","logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"","parse_status":"started"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"{\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"type","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"function","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"name","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"get","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Temperature","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"parameters","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" {\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"location","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Seattle","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\"}}","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":{"call_id":"e742df1f-0ae9-40ad-a49e-18e5c905484f","tool_name":"getTemperature","arguments":{"location":"Seattle"}},"parse_status":"success"},"logprobs":null,"stop_reason":"end_of_message"}}
data: {"event":{"event_type":"complete","delta":"","logprobs":null,"stop_reason":"end_of_message"}}
```

### Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "content": "1,2,3,",
    "stream": true,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 10
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}'
```

#### Non-Streaming Response
```
{
  "content": "4,5,6,7,8,",
  "stop_reason": "out_of_tokens",
  "logprobs": null
}
```

#### Streaming Response
```
data: {"delta":"4","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"5","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"6","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"7","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"8","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":"out_of_tokens","logprobs":null}
```

### Pre-Commit Checks
```
trim trailing whitespace.................................................Passed
check python ast.........................................................Passed
check for merge conflicts................................................Passed
check for added large files..............................................Passed
fix end of files.........................................................Passed
Insert license in comments...............................................Passed
flake8...................................................................Passed
Format files with µfmt...................................................Passed
```

### Testing with `test_inference.py`
```
$ export CEREBRAS_API_KEY=<insert API key here>
$ pytest -v -s llama_stack/providers/tests/inference/test_text_inference.py -m "cerebras and llama_8b" 
/net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/lib/python3.12/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"

  warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
=================================================== test session starts ===================================================
platform linux -- Python 3.12.3, pytest-8.3.3, pluggy-1.5.0 -- /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/bin/python3.12
cachedir: .pytest_cache
rootdir: /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack
configfile: pyproject.toml
plugins: anyio-4.6.2.post1, asyncio-0.24.0
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 128 items / 120 deselected / 8 selected                                                                         

llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_8b-cerebras] Resolved 4 providers
 inner-inference => cerebras
 models => __routing_table__
 inference => __autorouted__
 inspect => __builtin__

Models: meta-llama/Llama-3.1-8B-Instruct served by cerebras

PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_8b-cerebras] PASSED

================================ 6 passed, 2 skipped, 120 deselected, 6 warnings in 3.95s =================================
```

I ran `python llama_stack/scripts/distro_codegen.py` to run codegen.
2024-12-03 21:15:32 -08:00
dltn
beab798a1d Add initial direct client docs 2024-11-22 18:04:48 -08:00
Ashwin Bharambe
c2c53d0272 More doc cleanup 2024-11-22 14:37:22 -08:00
Renamed from docs/source/distribution_dev/building_distro.md (Browse further)