phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-24 05:14:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/llama_stack/templates/starter/run.yaml
Ben Browning 404708e99d fix: Ollama should be optional in starter distro 
Our starter distro required Ollama to be running (and a large list of
models available in that Ollama) to successfully start. This adjusts
things so that Ollama does not have to be running to use the starter
template / distro.

To accomplish this, a few changes were needed:

* The Ollama provider is now configurable whether it raises an
Exception or just logs a warning when it cannot reach the Ollama
server on startup. The default is to raise an exception (same as
previous behavior), but in the starter template we adjust this to just
log a warning so that we can bring the stack up without needing a
running Ollama server.

* The starter template no longer specifies a default list of models
for Ollama, as any models specified there need to actually be pulled
and available in Ollama. Instead, it adds a new
`OLLAMA_INFERENCE_MODEL` environment variable where users can provide
an optional model to register with the Ollama provider on
startup. Additional models can also be registered via the typical
`models.register(...)` at runtime.

* The vLLM template was adjusted to also allow an optional
`VLLM_INFERENCE_MODEL` specified on startup, so that the behavior
between vLLM and Ollama was consistent here to make it easy to get up
and running quickly.

* The default vector store was changed from sqlite-vec to
faiss. sqlite-vec can enabled via setting the `ENABLE_SQLITE_VEC`
environment variable, like we do for chromadb and pgvector. This is
due to sqlite-vec not shipping proper arm64 binaries, like we
previously fixed in #1530 for the ollama distribution.

With this change, the following scenarios now work with the starter
template that did not before:

* no Ollama running
* Ollama running but not all of the Llama models pulled locally
* Ollama running with a custom model registered on startup
* vLLM running with a custom model registered on startup
* running the starter template on linux/arm64, like when running
containers on Mac without rosetta emulation

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-06-25 09:04:45 -04:00

820 lines
26 KiB
YAML
Raw Blame History

version: '2'
image_name: starter
apis:
- agents
- datasetio
- eval
- files
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
api_key: ${env.FIREWORKS_API_KEY:}
- provider_id: together
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
raise_on_connect_error: false
- provider_id: anthropic
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY:}
- provider_id: gemini
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY:}
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:}
- provider_id: vllm
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:4096}
api_token: ${env.VLLM_API_TOKEN:fake}
tls_verify: ${env.VLLM_TLS_VERIFY:true}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/faiss_store.db
- provider_id: ${env.ENABLE_SQLITE_VEC+sqlite-vec}
provider_type: inline::sqlite-vec
config:
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/sqlite_vec.db
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:}
- provider_id: ${env.ENABLE_PGVECTOR+pgvector}
provider_type: remote::pgvector
config:
host: ${env.PGVECTOR_HOST:localhost}
port: ${env.PGVECTOR_PORT:5432}
db: ${env.PGVECTOR_DB:}
user: ${env.PGVECTOR_USER:}
password: ${env.PGVECTOR_PASSWORD:}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: ${env.FILES_STORAGE_DIR:~/.llama/distributions/starter/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/files_metadata.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
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/trace_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- 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
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/inference_store.db
models:
- metadata: {}
model_id: openai/gpt-4o
provider_id: openai
provider_model_id: openai/gpt-4o
model_type: llm
- metadata: {}
model_id: openai/gpt-4o-mini
provider_id: openai
provider_model_id: openai/gpt-4o-mini
model_type: llm
- metadata: {}
model_id: openai/chatgpt-4o-latest
provider_id: openai
provider_model_id: openai/chatgpt-4o-latest
model_type: llm
- metadata: {}
model_id: openai/gpt-3.5-turbo-0125
provider_id: openai
provider_model_id: gpt-3.5-turbo-0125
model_type: llm
- metadata: {}
model_id: openai/gpt-3.5-turbo
provider_id: openai
provider_model_id: gpt-3.5-turbo
model_type: llm
- metadata: {}
model_id: openai/gpt-3.5-turbo-instruct
provider_id: openai
provider_model_id: gpt-3.5-turbo-instruct
model_type: llm
- metadata: {}
model_id: openai/gpt-4
provider_id: openai
provider_model_id: gpt-4
model_type: llm
- metadata: {}
model_id: openai/gpt-4-turbo
provider_id: openai
provider_model_id: gpt-4-turbo
model_type: llm
- metadata: {}
model_id: openai/gpt-4o
provider_id: openai
provider_model_id: gpt-4o
model_type: llm
- metadata: {}
model_id: openai/gpt-4o-2024-08-06
provider_id: openai
provider_model_id: gpt-4o-2024-08-06
model_type: llm
- metadata: {}
model_id: openai/gpt-4o-mini
provider_id: openai
provider_model_id: gpt-4o-mini
model_type: llm
- metadata: {}
model_id: openai/gpt-4o-audio-preview
provider_id: openai
provider_model_id: gpt-4o-audio-preview
model_type: llm
- metadata: {}
model_id: openai/chatgpt-4o-latest
provider_id: openai
provider_model_id: chatgpt-4o-latest
model_type: llm
- metadata: {}
model_id: openai/o1
provider_id: openai
provider_model_id: o1
model_type: llm
- metadata: {}
model_id: openai/o1-mini
provider_id: openai
provider_model_id: o1-mini
model_type: llm
- metadata: {}
model_id: openai/o3-mini
provider_id: openai
provider_model_id: o3-mini
model_type: llm
- metadata: {}
model_id: openai/o4-mini
provider_id: openai
provider_model_id: o4-mini
model_type: llm
- metadata:
embedding_dimension: 1536
context_length: 8192
model_id: openai/text-embedding-3-small
provider_id: openai
provider_model_id: openai/text-embedding-3-small
model_type: embedding
- metadata:
embedding_dimension: 3072
context_length: 8192
model_id: openai/text-embedding-3-large
provider_id: openai
provider_model_id: openai/text-embedding-3-large
model_type: embedding
- metadata:
embedding_dimension: 1536
context_length: 8192
model_id: openai/text-embedding-3-small
provider_id: openai
provider_model_id: text-embedding-3-small
model_type: embedding
- metadata:
embedding_dimension: 3072
context_length: 8192
model_id: openai/text-embedding-3-large
provider_id: openai
provider_model_id: text-embedding-3-large
model_type: embedding
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.1-8B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.1-70B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.2-3B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-3.3-70B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-guard-3-8b
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-Guard-3-8B
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-guard-3-11b-vision
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-Guard-3-11B-Vision
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama4-scout-instruct-basic
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata: {}
model_id: fireworks/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192
model_id: fireworks/nomic-ai/nomic-embed-text-v1.5
provider_id: fireworks
provider_model_id: nomic-ai/nomic-embed-text-v1.5
model_type: embedding
- metadata: {}
model_id: together/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.1-8B-Instruct
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.1-70B-Instruct
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: together
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-3B-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-3B-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.3-70B-Instruct-Turbo
provider_id: together
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-3.3-70B-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Meta-Llama-Guard-3-8B
provider_id: together
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-Guard-3-8B
provider_id: together
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-Guard-3-11B-Vision-Turbo
provider_id: together
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-Guard-3-11B-Vision
provider_id: together
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192
model_id: togethercomputer/m2-bert-80M-8k-retrieval
provider_id: together
provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval
model_type: embedding
- metadata:
embedding_dimension: 768
context_length: 32768
model_id: togethercomputer/m2-bert-80M-32k-retrieval
provider_id: together
provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
model_type: embedding
- metadata: {}
model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: together
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: together
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: ollama/${env.OLLAMA_INFERENCE_MODEL:__disabled__}
provider_id: ollama
provider_model_id: ${env.OLLAMA_INFERENCE_MODEL:__disabled__}
model_type: llm
- metadata: {}
model_id: anthropic/claude-3-5-sonnet-latest
provider_id: anthropic
provider_model_id: anthropic/claude-3-5-sonnet-latest
model_type: llm
- metadata: {}
model_id: anthropic/claude-3-7-sonnet-latest
provider_id: anthropic
provider_model_id: anthropic/claude-3-7-sonnet-latest
model_type: llm
- metadata: {}
model_id: anthropic/claude-3-5-haiku-latest
provider_id: anthropic
provider_model_id: anthropic/claude-3-5-haiku-latest
model_type: llm
- metadata:
embedding_dimension: 1024
context_length: 32000
model_id: anthropic/voyage-3
provider_id: anthropic
provider_model_id: anthropic/voyage-3
model_type: embedding
- metadata:
embedding_dimension: 512
context_length: 32000
model_id: anthropic/voyage-3-lite
provider_id: anthropic
provider_model_id: anthropic/voyage-3-lite
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 32000
model_id: anthropic/voyage-code-3
provider_id: anthropic
provider_model_id: anthropic/voyage-code-3
model_type: embedding
- metadata: {}
model_id: gemini/gemini-1.5-flash
provider_id: gemini
provider_model_id: gemini/gemini-1.5-flash
model_type: llm
- metadata: {}
model_id: gemini/gemini-1.5-pro
provider_id: gemini
provider_model_id: gemini/gemini-1.5-pro
model_type: llm
- metadata: {}
model_id: gemini/gemini-2.0-flash
provider_id: gemini
provider_model_id: gemini/gemini-2.0-flash
model_type: llm
- metadata: {}
model_id: gemini/gemini-2.5-flash
provider_id: gemini
provider_model_id: gemini/gemini-2.5-flash
model_type: llm
- metadata: {}
model_id: gemini/gemini-2.5-pro
provider_id: gemini
provider_model_id: gemini/gemini-2.5-pro
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 2048
model_id: gemini/text-embedding-004
provider_id: gemini
provider_model_id: gemini/text-embedding-004
model_type: embedding
- metadata: {}
model_id: groq/llama3-8b-8192
provider_id: groq
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-3.1-8B-Instruct
provider_id: groq
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: groq/llama-3.1-8b-instant
provider_id: groq
provider_model_id: groq/llama-3.1-8b-instant
model_type: llm
- metadata: {}
model_id: groq/llama3-70b-8192
provider_id: groq
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-3-70B-Instruct
provider_id: groq
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: groq/llama-3.3-70b-versatile
provider_id: groq
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-3.3-70B-Instruct
provider_id: groq
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: groq/llama-3.2-3b-preview
provider_id: groq
provider_model_id: groq/llama-3.2-3b-preview
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-3.2-3B-Instruct
provider_id: groq
provider_model_id: groq/llama-3.2-3b-preview
model_type: llm
- metadata: {}
model_id: groq/llama-4-scout-17b-16e-instruct
provider_id: groq
provider_model_id: groq/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: groq
provider_model_id: groq/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
provider_id: groq
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: groq
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: groq/llama-4-maverick-17b-128e-instruct
provider_id: groq
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: groq
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
provider_id: groq
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: groq/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: groq
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-3.1-8B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.1-8B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-3.1-405B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-3.2-1B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.2-1B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-3.2-3B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.2-3B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-3.3-70B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.3-70B-Instruct
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: sambanova
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: sambanova/Meta-Llama-Guard-3-8B
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: sambanova/meta-llama/Llama-Guard-3-8B
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: vllm/${env.VLLM_INFERENCE_MODEL:__disabled__}
provider_id: vllm
provider_model_id: ${env.VLLM_INFERENCE_MODEL:__disabled__}
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
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
Reference in a new issue View git blame Copy permalink