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

CLI Update: build -> configure -> run (#69)

Browse source 
* remove configure from build

* remove config from build

* configure to regenerate file

* update memory providers

* remove comments

* udpate build script

* add reedme

* update doc

* rename getting started

* update build cli

* update docker build script

* configure update

* clean up configure

* [tmp fix] hardware requirement tmp fix

* clean up build

* fix configure

* add example build files for conda & docker

* remove resolve_distribution_spec

* remove available_distribution_specs

* example build files

* update example build files

* more clean up on build

* add name args to override name

* move distribution to yaml files

* generate distribution specs

* getting started guide

* getting started

* add build yaml to Dockerfile

* cleanup distribution_dependencies

* configure from  docker image name

* build relative paths

* minor comment

* getting started

* Update getting_started.md

* Update getting_started.md

* address comments, configure within docker file

* remove distribution types!

* update getting started

* update documentation

* remove listing distribution

* minor heading

* address nits, remove docker_image=null

* gitignore
This commit is contained in:
Xi Yan 2024-09-16 11:02:26 -07:00 • committed by GitHub
parent 73b71d9689
commit d9147f3184
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 759 additions and 512 deletions
Download patch file Download diff file Expand all files Collapse all files

83
llama_toolchain/core/distribution_registry.py
View file

@ -5,84 +5,19 @@
# the root directory of this source tree.
from functools import lru_cache
from pathlib import Path
from typing import List, Optional
from .datatypes import * # noqa: F403
import yaml
@lru_cache()
def available_distribution_specs() -> List[DistributionSpec]:
return [
DistributionSpec(
distribution_type="local",
description="Use code from `llama_toolchain` itself to serve all llama stack APIs",
providers={
Api.inference: "meta-reference",
Api.memory: "meta-reference-faiss",
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.telemetry: "console",
},
),
DistributionSpec(
distribution_type="remote",
description="Point to remote services for all llama stack APIs",
providers={
**{x: "remote" for x in Api},
Api.telemetry: "console",
},
),
DistributionSpec(
distribution_type="local-ollama",
description="Like local, but use ollama for running LLM inference",
providers={
Api.inference: remote_provider_type("ollama"),
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.memory: "meta-reference-faiss",
Api.telemetry: "console",
},
),
DistributionSpec(
distribution_type="local-plus-fireworks-inference",
description="Use Fireworks.ai for running LLM inference",
providers={
Api.inference: remote_provider_type("fireworks"),
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.memory: "meta-reference-faiss",
Api.telemetry: "console",
},
),
DistributionSpec(
distribution_type="local-plus-together-inference",
description="Use Together.ai for running LLM inference",
providers={
Api.inference: remote_provider_type("together"),
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.memory: "meta-reference-faiss",
Api.telemetry: "console",
},
),
DistributionSpec(
distribution_type="local-plus-tgi-inference",
description="Use TGI for running LLM inference",
providers={
Api.inference: remote_provider_type("tgi"),
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.memory: "meta-reference-faiss",
},
),
]
distribution_specs = []
for p in Path("llama_toolchain/configs/distributions/distribution_registry").rglob(
"*.yaml"
):
with open(p, "r") as f:
distribution_specs.append(DistributionSpec(**yaml.safe_load(f)))
@lru_cache()
def resolve_distribution_spec(
distribution_type: str,
) -> Optional[DistributionSpec]:
for spec in available_distribution_specs():
if spec.distribution_type == distribution_type:
return spec
return None
return distribution_specs