mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-12 13:00:39 +00:00
chore: rename templates to distributions (#3035)
As the title says. Distributions is in, Templates is out. `llama stack build --template` --> `llama stack build --distro`. For backward compatibility, the previous option is kept but results in a warning. Updated `server.py` to remove the "config_or_template" backward compatibility since it has been a couple releases since that change.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
12f964437a
commit
cc87995e2b
87 changed files with 263 additions and 330 deletions
7
llama_stack/distributions/meta-reference-gpu/__init__.py
Normal file
7
llama_stack/distributions/meta-reference-gpu/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# 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 .meta_reference import get_distribution_template # noqa: F401
|
||||
34
llama_stack/distributions/meta-reference-gpu/build.yaml
Normal file
34
llama_stack/distributions/meta-reference-gpu/build.yaml
Normal file
|
|
@ -0,0 +1,34 @@
|
|||
version: 2
|
||||
distribution_spec:
|
||||
description: Use Meta Reference for running LLM inference
|
||||
providers:
|
||||
inference:
|
||||
- provider_type: inline::meta-reference
|
||||
vector_io:
|
||||
- provider_type: inline::faiss
|
||||
- provider_type: remote::chromadb
|
||||
- provider_type: remote::pgvector
|
||||
safety:
|
||||
- provider_type: inline::llama-guard
|
||||
agents:
|
||||
- provider_type: inline::meta-reference
|
||||
telemetry:
|
||||
- provider_type: inline::meta-reference
|
||||
eval:
|
||||
- provider_type: inline::meta-reference
|
||||
datasetio:
|
||||
- provider_type: remote::huggingface
|
||||
- provider_type: inline::localfs
|
||||
scoring:
|
||||
- provider_type: inline::basic
|
||||
- provider_type: inline::llm-as-judge
|
||||
- provider_type: inline::braintrust
|
||||
tool_runtime:
|
||||
- provider_type: remote::brave-search
|
||||
- provider_type: remote::tavily-search
|
||||
- provider_type: inline::rag-runtime
|
||||
- provider_type: remote::model-context-protocol
|
||||
image_type: venv
|
||||
additional_pip_packages:
|
||||
- aiosqlite
|
||||
- sqlalchemy[asyncio]
|
||||
113
llama_stack/distributions/meta-reference-gpu/doc_template.md
Normal file
113
llama_stack/distributions/meta-reference-gpu/doc_template.md
Normal file
|
|
@ -0,0 +1,113 @@
|
|||
---
|
||||
orphan: true
|
||||
---
|
||||
# Meta Reference Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
|
||||
|
||||
{{ providers_table }}
|
||||
|
||||
Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.
|
||||
|
||||
{% if run_config_env_vars %}
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
{% for var, (default_value, description) in run_config_env_vars.items() %}
|
||||
- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
|
||||
{% endfor %}
|
||||
{% endif %}
|
||||
|
||||
|
||||
## Prerequisite: Downloading Models
|
||||
|
||||
Please use `llama model list --downloaded` to check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/references/llama_cli_reference/download_models.html) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
|
||||
|
||||
```
|
||||
$ llama model list --downloaded
|
||||
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
|
||||
┃ Model ┃ Size ┃ Modified Time ┃
|
||||
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
|
||||
│ Llama3.2-1B-Instruct:int4-qlora-eo8 │ 1.53 GB │ 2025-02-26 11:22:28 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama3.2-1B │ 2.31 GB │ 2025-02-18 21:48:52 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Prompt-Guard-86M │ 0.02 GB │ 2025-02-26 11:29:28 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama3.2-3B-Instruct:int4-spinquant-eo8 │ 3.69 GB │ 2025-02-26 11:37:41 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama3.2-3B │ 5.99 GB │ 2025-02-18 21:51:26 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama3.1-8B │ 14.97 GB │ 2025-02-16 10:36:37 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama3.2-1B-Instruct:int4-spinquant-eo8 │ 1.51 GB │ 2025-02-26 11:35:02 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama-Guard-3-1B │ 2.80 GB │ 2025-02-26 11:20:46 │
|
||||
├─────────────────────────────────────────┼──────────┼─────────────────────┤
|
||||
│ Llama-Guard-3-1B:int4 │ 0.43 GB │ 2025-02-26 11:33:33 │
|
||||
└─────────────────────────────────────────┴──────────┴─────────────────────┘
|
||||
```
|
||||
|
||||
## Running the Distribution
|
||||
|
||||
You can do this via venv or Docker which has a pre-built image.
|
||||
|
||||
### Via Docker
|
||||
|
||||
This method allows you to get started quickly without having to build the distribution code.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=8321
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
--gpu all \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
--gpu all \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
|
||||
### Via venv
|
||||
|
||||
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
|
||||
|
||||
```bash
|
||||
llama stack build --distro {{ name }} --image-type venv
|
||||
llama stack run distributions/{{ name }}/run.yaml \
|
||||
--port 8321 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run distributions/{{ name }}/run-with-safety.yaml \
|
||||
--port 8321 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
164
llama_stack/distributions/meta-reference-gpu/meta_reference.py
Normal file
164
llama_stack/distributions/meta-reference-gpu/meta_reference.py
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
# 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 import ModelType
|
||||
from llama_stack.core.datatypes import (
|
||||
BuildProvider,
|
||||
ModelInput,
|
||||
Provider,
|
||||
ShieldInput,
|
||||
ToolGroupInput,
|
||||
)
|
||||
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
|
||||
from llama_stack.providers.inline.inference.meta_reference import (
|
||||
MetaReferenceInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": [BuildProvider(provider_type="inline::meta-reference")],
|
||||
"vector_io": [
|
||||
BuildProvider(provider_type="inline::faiss"),
|
||||
BuildProvider(provider_type="remote::chromadb"),
|
||||
BuildProvider(provider_type="remote::pgvector"),
|
||||
],
|
||||
"safety": [BuildProvider(provider_type="inline::llama-guard")],
|
||||
"agents": [BuildProvider(provider_type="inline::meta-reference")],
|
||||
"telemetry": [BuildProvider(provider_type="inline::meta-reference")],
|
||||
"eval": [BuildProvider(provider_type="inline::meta-reference")],
|
||||
"datasetio": [
|
||||
BuildProvider(provider_type="remote::huggingface"),
|
||||
BuildProvider(provider_type="inline::localfs"),
|
||||
],
|
||||
"scoring": [
|
||||
BuildProvider(provider_type="inline::basic"),
|
||||
BuildProvider(provider_type="inline::llm-as-judge"),
|
||||
BuildProvider(provider_type="inline::braintrust"),
|
||||
],
|
||||
"tool_runtime": [
|
||||
BuildProvider(provider_type="remote::brave-search"),
|
||||
BuildProvider(provider_type="remote::tavily-search"),
|
||||
BuildProvider(provider_type="inline::rag-runtime"),
|
||||
BuildProvider(provider_type="remote::model-context-protocol"),
|
||||
],
|
||||
}
|
||||
name = "meta-reference-gpu"
|
||||
inference_provider = Provider(
|
||||
provider_id="meta-reference-inference",
|
||||
provider_type="inline::meta-reference",
|
||||
config=MetaReferenceInferenceConfig.sample_run_config(
|
||||
model="${env.INFERENCE_MODEL}",
|
||||
checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:=null}",
|
||||
),
|
||||
)
|
||||
embedding_provider = Provider(
|
||||
provider_id="sentence-transformers",
|
||||
provider_type="inline::sentence-transformers",
|
||||
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
||||
)
|
||||
vector_io_provider = Provider(
|
||||
provider_id="faiss",
|
||||
provider_type="inline::faiss",
|
||||
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="meta-reference-inference",
|
||||
)
|
||||
embedding_model = ModelInput(
|
||||
model_id="all-MiniLM-L6-v2",
|
||||
provider_id="sentence-transformers",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 384,
|
||||
},
|
||||
)
|
||||
safety_model = ModelInput(
|
||||
model_id="${env.SAFETY_MODEL}",
|
||||
provider_id="meta-reference-safety",
|
||||
)
|
||||
default_tool_groups = [
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::websearch",
|
||||
provider_id="tavily-search",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
]
|
||||
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
description="Use Meta Reference for running LLM inference",
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider, embedding_provider],
|
||||
"vector_io": [vector_io_provider],
|
||||
},
|
||||
default_models=[inference_model, embedding_model],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
"run-with-safety.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [
|
||||
inference_provider,
|
||||
embedding_provider,
|
||||
Provider(
|
||||
provider_id="meta-reference-safety",
|
||||
provider_type="inline::meta-reference",
|
||||
config=MetaReferenceInferenceConfig.sample_run_config(
|
||||
model="${env.SAFETY_MODEL}",
|
||||
checkpoint_dir="${env.SAFETY_CHECKPOINT_DIR:=null}",
|
||||
),
|
||||
),
|
||||
],
|
||||
"vector_io": [vector_io_provider],
|
||||
},
|
||||
default_models=[
|
||||
inference_model,
|
||||
safety_model,
|
||||
embedding_model,
|
||||
],
|
||||
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model loaded into the Meta Reference server",
|
||||
),
|
||||
"INFERENCE_CHECKPOINT_DIR": (
|
||||
"null",
|
||||
"Directory containing the Meta Reference model checkpoint",
|
||||
),
|
||||
"SAFETY_MODEL": (
|
||||
"meta-llama/Llama-Guard-3-1B",
|
||||
"Name of the safety (Llama-Guard) model to use",
|
||||
),
|
||||
"SAFETY_CHECKPOINT_DIR": (
|
||||
"null",
|
||||
"Directory containing the Llama-Guard model checkpoint",
|
||||
),
|
||||
},
|
||||
)
|
||||
|
|
@ -0,0 +1,143 @@
|
|||
version: 2
|
||||
image_name: meta-reference-gpu
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: meta-reference-inference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
model: ${env.INFERENCE_MODEL}
|
||||
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
|
||||
quantization:
|
||||
type: ${env.QUANTIZATION_TYPE:=bf16}
|
||||
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
|
||||
max_batch_size: ${env.MAX_BATCH_SIZE:=1}
|
||||
max_seq_len: ${env.MAX_SEQ_LEN:=4096}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
- provider_id: meta-reference-safety
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
model: ${env.SAFETY_MODEL}
|
||||
checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:=null}
|
||||
quantization:
|
||||
type: ${env.QUANTIZATION_TYPE:=bf16}
|
||||
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
|
||||
max_batch_size: ${env.MAX_BATCH_SIZE:=1}
|
||||
max_seq_len: ${env.MAX_SEQ_LEN:=4096}
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/trace_store.db
|
||||
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
- provider_id: braintrust
|
||||
provider_type: inline::braintrust
|
||||
config:
|
||||
openai_api_key: ${env.OPENAI_API_KEY:=}
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
config:
|
||||
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: tavily-search
|
||||
provider_type: remote::tavily-search
|
||||
config:
|
||||
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: meta-reference-inference
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: ${env.SAFETY_MODEL}
|
||||
provider_id: meta-reference-safety
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 384
|
||||
model_id: all-MiniLM-L6-v2
|
||||
provider_id: sentence-transformers
|
||||
model_type: embedding
|
||||
shields:
|
||||
- shield_id: ${env.SAFETY_MODEL}
|
||||
vector_dbs: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
benchmarks: []
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
- toolgroup_id: builtin::rag
|
||||
provider_id: rag-runtime
|
||||
server:
|
||||
port: 8321
|
||||
128
llama_stack/distributions/meta-reference-gpu/run.yaml
Normal file
128
llama_stack/distributions/meta-reference-gpu/run.yaml
Normal file
|
|
@ -0,0 +1,128 @@
|
|||
version: 2
|
||||
image_name: meta-reference-gpu
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: meta-reference-inference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
model: ${env.INFERENCE_MODEL}
|
||||
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
|
||||
quantization:
|
||||
type: ${env.QUANTIZATION_TYPE:=bf16}
|
||||
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
|
||||
max_batch_size: ${env.MAX_BATCH_SIZE:=1}
|
||||
max_seq_len: ${env.MAX_SEQ_LEN:=4096}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/trace_store.db
|
||||
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
- provider_id: braintrust
|
||||
provider_type: inline::braintrust
|
||||
config:
|
||||
openai_api_key: ${env.OPENAI_API_KEY:=}
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
config:
|
||||
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: tavily-search
|
||||
provider_type: remote::tavily-search
|
||||
config:
|
||||
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: meta-reference-inference
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 384
|
||||
model_id: all-MiniLM-L6-v2
|
||||
provider_id: sentence-transformers
|
||||
model_type: embedding
|
||||
shields: []
|
||||
vector_dbs: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
benchmarks: []
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
- toolgroup_id: builtin::rag
|
||||
provider_id: rag-runtime
|
||||
server:
|
||||
port: 8321
|
||||
Loading…
Add table
Add a link
Reference in a new issue