mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-30 22:13:52 +00:00
Add support for RamaLama
RamaLama is a fully Open Source AI Model tool that facilitate local management of AI Models. https://github.com/containers/ramalama It is fully open source and supports pulling models from HuggingFace, Ollama, OCI Images, and via URI file://, http://, https:// It uses the llama.cpp and vllm AI engines for running the MODELS. It also defaults to running the models inside of containers. Signed-off-by: Daniel J Walsh <dwalsh@redhat.com>
This commit is contained in:
Daniel J Walsh
parent
5f90be5388
commit
9120e07d9d
7 changed files with 665 additions and 0 deletions
162
llama_stack/templates/ramalama/ollama.py
Normal file
162
llama_stack/templates/ramalama/ollama.py
Normal file
|
|
@ -0,0 +1,162 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.apis.models.models import ModelType
|
||||
from llama_stack.distribution.datatypes import (
|
||||
ModelInput,
|
||||
Provider,
|
||||
ShieldInput,
|
||||
ToolGroupInput,
|
||||
)
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
|
||||
from llama_stack.providers.remote.inference.ramalama import RamaLamaImplConfig
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::ramalama"],
|
||||
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
"eval": ["inline::meta-reference"],
|
||||
"datasetio": ["remote::huggingface", "inline::localfs"],
|
||||
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
||||
"tool_runtime": [
|
||||
"remote::brave-search",
|
||||
"remote::tavily-search",
|
||||
"inline::code-interpreter",
|
||||
"inline::rag-runtime",
|
||||
],
|
||||
}
|
||||
name = "ramalama"
|
||||
inference_provider = Provider(
|
||||
provider_id="ramalama",
|
||||
provider_type="remote::ramalama",
|
||||
config=RamaLamaImplConfig.sample_run_config(),
|
||||
)
|
||||
embedding_provider = Provider(
|
||||
provider_id="sentence-transformers",
|
||||
provider_type="inline::sentence-transformers",
|
||||
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
||||
)
|
||||
vector_io_provider = Provider(
|
||||
provider_id="faiss",
|
||||
provider_type="inline::faiss",
|
||||
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="ramalama",
|
||||
)
|
||||
safety_model = ModelInput(
|
||||
model_id="${env.SAFETY_MODEL}",
|
||||
provider_id="ramalama",
|
||||
)
|
||||
embedding_model = ModelInput(
|
||||
model_id="all-MiniLM-L6-v2",
|
||||
provider_id="sentence-transformers",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 384,
|
||||
},
|
||||
)
|
||||
default_tool_groups = [
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::websearch",
|
||||
provider_id="tavily-search",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::code_interpreter",
|
||||
provider_id="code-interpreter",
|
||||
),
|
||||
]
|
||||
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
description="Use (an external) RamaLama server for running LLM inference",
|
||||
container_image=None,
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
default_models=[inference_model, safety_model],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider, embedding_provider],
|
||||
"vector_io": [vector_io_provider],
|
||||
},
|
||||
default_models=[inference_model, embedding_model],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
"run-with-safety.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [
|
||||
inference_provider,
|
||||
embedding_provider,
|
||||
],
|
||||
"vector_io": [vector_io_provider],
|
||||
"safety": [
|
||||
Provider(
|
||||
provider_id="llama-guard",
|
||||
provider_type="inline::llama-guard",
|
||||
config={},
|
||||
),
|
||||
Provider(
|
||||
provider_id="code-scanner",
|
||||
provider_type="inline::code-scanner",
|
||||
config={},
|
||||
),
|
||||
],
|
||||
},
|
||||
default_models=[
|
||||
inference_model,
|
||||
safety_model,
|
||||
embedding_model,
|
||||
],
|
||||
default_shields=[
|
||||
ShieldInput(
|
||||
shield_id="${env.SAFETY_MODEL}",
|
||||
provider_id="llama-guard",
|
||||
),
|
||||
ShieldInput(
|
||||
shield_id="CodeScanner",
|
||||
provider_id="code-scanner",
|
||||
),
|
||||
],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"OLLAMA_URL": (
|
||||
"http://127.0.0.1:11434",
|
||||
"URL of the RamaLama server",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model loaded into the RamaLama server",
|
||||
),
|
||||
"SAFETY_MODEL": (
|
||||
"meta-llama/Llama-Guard-3-1B",
|
||||
"Safety model loaded into the RamaLama server",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue