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

feat: implement get chat completions APIs (#2200)

Browse source 
# What does this PR do?
* Provide sqlite implementation of the APIs introduced in
https://github.com/meta-llama/llama-stack/pull/2145.
* Introduced a SqlStore API: llama_stack/providers/utils/sqlstore/api.py
and the first Sqlite implementation
* Pagination support will be added in a future PR.

## Test Plan
Unit test on sql store:
<img width="1005" alt="image"
src="https://github.com/user-attachments/assets/9b8b7ec8-632b-4667-8127-5583426b2e29"
/>


Integration test:
```
INFERENCE_MODEL="llama3.2:3b-instruct-fp16" llama stack build --template ollama --image-type conda --run
```
```
LLAMA_STACK_CONFIG=http://localhost:5001 INFERENCE_MODEL="llama3.2:3b-instruct-fp16" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-fp16" -k 'inference_store and openai'
```
This commit is contained in:
ehhuang 2025-05-21 22:21:52 -07:00 • committed by GitHub
parent 633bb9c5b3
commit 549812f51e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
71 changed files with 1111 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/templates/template.py
View file

@ -29,6 +29,7 @@ from llama_stack.distribution.distribution import get_provider_registry
from llama_stack.distribution.utils.dynamic import instantiate_class_type
from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
def get_model_registry(
@ -117,6 +118,10 @@ class RunConfigSettings(BaseModel):
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="registry.db",
),
inference_store=SqliteSqlStoreConfig.sample_run_config(
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="inference_store.db",
),
models=self.default_models or [],
shields=self.default_shields or [],
tool_groups=self.default_tool_groups or [],
@ -146,14 +151,20 @@ class DistributionTemplate(BaseModel):
available_models_by_provider: dict[str, list[ProviderModelEntry]] | None = None
def build_config(self) -> BuildConfig:
additional_pip_packages: list[str] = []
for run_config in self.run_configs.values():
run_config_ = run_config.run_config(self.name, self.providers, self.container_image)
if run_config_.inference_store:
additional_pip_packages.extend(run_config_.inference_store.pip_packages)
return BuildConfig(
name=self.name,
distribution_spec=DistributionSpec(
description=self.description,
container_image=self.container_image,
providers=self.providers,
),
image_type="conda", # default to conda, can be overridden
additional_pip_packages=additional_pip_packages,
)
def generate_markdown_docs(self) -> str: