llama-stack-mirror/llama_stack/templates/starter/run.yaml
Derek Higgins c2b64dce5b
fix: Move sentence-transformers to the top (#2703)
Move sentence-transformers to be the first embedding in the list of
models. This ensures it will always be the default and is more
consistent then having the default change based on what env variables
are available

Closes: #2702

## Test Plan
Manually verified

Signed-off-by: Derek Higgins <derekh@redhat.com>
2025-07-17 10:31:30 -04:00

1189 lines
48 KiB
YAML

version: 2
image_name: starter
apis:
- agents
- datasetio
- eval
- files
- inference
- post_training
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
api_key: ${env.CEREBRAS_API_KEY}
- provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
- provider_id: ${env.ENABLE_VLLM:=__disabled__}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
- provider_id: ${env.ENABLE_TGI:=__disabled__}
provider_type: remote::tgi
config:
url: ${env.TGI_URL}
- provider_id: ${env.ENABLE_HF_SERVERLESS:=__disabled__}
provider_type: remote::hf::serverless
config:
huggingface_repo: ${env.INFERENCE_MODEL}
api_token: ${env.HF_API_TOKEN}
- provider_id: ${env.ENABLE_HF_ENDPOINT:=__disabled__}
provider_type: remote::hf::endpoint
config:
endpoint_name: ${env.INFERENCE_ENDPOINT_NAME}
api_token: ${env.HF_API_TOKEN}
- provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
api_key: ${env.FIREWORKS_API_KEY}
- provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
- provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_type: remote::bedrock
config: {}
- provider_id: ${env.ENABLE_DATABRICKS:=__disabled__}
provider_type: remote::databricks
config:
url: ${env.DATABRICKS_URL}
api_token: ${env.DATABRICKS_API_TOKEN}
- provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_type: remote::runpod
config:
url: ${env.RUNPOD_URL:=}
api_token: ${env.RUNPOD_API_TOKEN}
- provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY}
- provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY}
- provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY}
- provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY}
- provider_id: ${env.ENABLE_FIREWORKS_OPENAI_COMPAT:=__disabled__}
provider_type: remote::fireworks-openai-compat
config:
openai_compat_api_base: https://api.fireworks.ai/inference/v1
api_key: ${env.FIREWORKS_API_KEY}
- provider_id: ${env.ENABLE_LLAMA_OPENAI_COMPAT:=__disabled__}
provider_type: remote::llama-openai-compat
config:
openai_compat_api_base: https://api.llama.com/compat/v1/
api_key: ${env.LLAMA_API_KEY}
- provider_id: ${env.ENABLE_TOGETHER_OPENAI_COMPAT:=__disabled__}
provider_type: remote::together-openai-compat
config:
openai_compat_api_base: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
- provider_id: ${env.ENABLE_GROQ_OPENAI_COMPAT:=__disabled__}
provider_type: remote::groq-openai-compat
config:
openai_compat_api_base: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY}
- provider_id: ${env.ENABLE_SAMBANOVA_OPENAI_COMPAT:=__disabled__}
provider_type: remote::sambanova-openai-compat
config:
openai_compat_api_base: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY}
- provider_id: ${env.ENABLE_CEREBRAS_OPENAI_COMPAT:=__disabled__}
provider_type: remote::cerebras-openai-compat
config:
openai_compat_api_base: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY}
- provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY}
- provider_id: ${env.ENABLE_PASSTHROUGH:=__disabled__}
provider_type: remote::passthrough
config:
url: ${env.PASSTHROUGH_URL}
api_key: ${env.PASSTHROUGH_API_KEY}
- provider_id: ${env.ENABLE_SENTENCE_TRANSFORMERS:=sentence-transformers}
provider_type: inline::sentence-transformers
config: {}
vector_io:
- provider_id: ${env.ENABLE_FAISS:=faiss}
provider_type: inline::faiss
config:
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/faiss_store.db
- provider_id: ${env.ENABLE_SQLITE_VEC:=__disabled__}
provider_type: inline::sqlite-vec
config:
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec_registry.db
- provider_id: ${env.ENABLE_MILVUS:=__disabled__}
provider_type: inline::milvus
config:
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/milvus_registry.db
- provider_id: ${env.ENABLE_CHROMADB:=__disabled__}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
- provider_id: ${env.ENABLE_PGVECTOR:=__disabled__}
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:=}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/pgvector_registry.db
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
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
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
post_training:
- provider_id: huggingface
provider_type: inline::huggingface
config:
checkpoint_format: huggingface
distributed_backend: null
device: cpu
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
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
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
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:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ${env.ENABLE_SENTENCE_TRANSFORMERS:=sentence-transformers}
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/llama3.1-8b
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/llama-3.3-70b
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama-3.3-70b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama-3.3-70b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/llama-4-scout-17b-16e-instruct
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_CEREBRAS:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_CEREBRAS:=__disabled__}
provider_model_id: llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.OLLAMA_INFERENCE_MODEL:=__disabled__}
provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
provider_model_id: ${env.OLLAMA_INFERENCE_MODEL:=__disabled__}
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.SAFETY_MODEL:=__disabled__}
provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
provider_model_id: ${env.SAFETY_MODEL:=__disabled__}
model_type: llm
- metadata:
embedding_dimension: ${env.OLLAMA_EMBEDDING_DIMENSION:=384}
model_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.OLLAMA_EMBEDDING_MODEL:=__disabled__}
provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
provider_model_id: ${env.OLLAMA_EMBEDDING_MODEL:=__disabled__}
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_VLLM:=__disabled__}/${env.VLLM_INFERENCE_MODEL:=__disabled__}
provider_id: ${env.ENABLE_VLLM:=__disabled__}
provider_model_id: ${env.VLLM_INFERENCE_MODEL:=__disabled__}
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p1-8b-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p1-70b-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.1-70B-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p1-405b-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p2-11b-vision-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p2-90b-vision-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-v3p3-70b-instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama4-scout-instruct-basic
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama4-maverick-instruct-basic
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/nomic-ai/nomic-embed-text-v1.5
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: nomic-ai/nomic-embed-text-v1.5
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-guard-3-8b
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-Guard-3-8B
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/accounts/fireworks/models/llama-guard-3-11b-vision
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_FIREWORKS:=__disabled__}/meta-llama/Llama-Guard-3-11B-Vision
provider_id: ${env.ENABLE_FIREWORKS:=__disabled__}
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.1-70B-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/togethercomputer/m2-bert-80M-8k-retrieval
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval
model_type: embedding
- metadata:
embedding_dimension: 768
context_length: 32768
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/togethercomputer/m2-bert-80M-32k-retrieval
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/together/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-Guard-3-8B
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-Guard-3-8B
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-Guard-3-11B-Vision-Turbo
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_TOGETHER:=__disabled__}/meta-llama/Llama-Guard-3-11B-Vision
provider_id: ${env.ENABLE_TOGETHER:=__disabled__}
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta.llama3-1-8b-instruct-v1:0
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-8b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-8b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta.llama3-1-70b-instruct-v1:0
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-70b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta-llama/Llama-3.1-70B-Instruct
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-70b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta.llama3-1-405b-instruct-v1:0
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-405b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_BEDROCK:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_BEDROCK:=__disabled__}
provider_model_id: meta.llama3-1-405b-instruct-v1:0
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_DATABRICKS:=__disabled__}/databricks-meta-llama-3-1-70b-instruct
provider_id: ${env.ENABLE_DATABRICKS:=__disabled__}
provider_model_id: databricks-meta-llama-3-1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_DATABRICKS:=__disabled__}/meta-llama/Llama-3.1-70B-Instruct
provider_id: ${env.ENABLE_DATABRICKS:=__disabled__}
provider_model_id: databricks-meta-llama-3-1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_DATABRICKS:=__disabled__}/databricks-meta-llama-3-1-405b-instruct
provider_id: ${env.ENABLE_DATABRICKS:=__disabled__}
provider_model_id: databricks-meta-llama-3-1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_DATABRICKS:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_DATABRICKS:=__disabled__}
provider_model_id: databricks-meta-llama-3-1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama3-8b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama3-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3-8B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama3-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama3-70b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama3-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3-70B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama3-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.1-8b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-8b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.1-70b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.1-70B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.1-405b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.1-405b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.2-1b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-1b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.2-1B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-1b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.2-3b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-3b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-3b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.2-11b-vision-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.2-90b-vision-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta/llama-3.3-70b-instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata:
embedding_dimension: 2048
context_length: 8192
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/nvidia/llama-3.2-nv-embedqa-1b-v2
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/nvidia/nv-embedqa-e5-v5
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: nvidia/nv-embedqa-e5-v5
model_type: embedding
- metadata:
embedding_dimension: 4096
context_length: 512
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/nvidia/nv-embedqa-mistral-7b-v2
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: ${env.ENABLE_NVIDIA:=__disabled__}/snowflake/arctic-embed-l
provider_id: ${env.ENABLE_NVIDIA:=__disabled__}
provider_model_id: snowflake/arctic-embed-l
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-8B
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-8B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-70B
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-70B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B:bf16-mp8
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B:bf16-mp8
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B:bf16-mp16
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B:bf16-mp16
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-8B-Instruct
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-70B-Instruct
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-70B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B-Instruct:bf16-mp8
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B-Instruct:bf16-mp8
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B-Instruct
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.1-405B-Instruct:bf16-mp16
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.1-405B-Instruct:bf16-mp16
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.2-1B
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.2-1B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_RUNPOD:=__disabled__}/Llama3.2-3B
provider_id: ${env.ENABLE_RUNPOD:=__disabled__}
provider_model_id: Llama3.2-3B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: openai/gpt-4o
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/gpt-4o-mini
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: openai/gpt-4o-mini
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/chatgpt-4o-latest
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: openai/chatgpt-4o-latest
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-3.5-turbo-0125
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-3.5-turbo-0125
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-3.5-turbo
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-3.5-turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-3.5-turbo-instruct
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-3.5-turbo-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4-turbo
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4-turbo
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4o
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4o
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4o-2024-08-06
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4o-2024-08-06
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4o-mini
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4o-mini
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/gpt-4o-audio-preview
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: gpt-4o-audio-preview
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/chatgpt-4o-latest
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: chatgpt-4o-latest
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/o1
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: o1
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/o1-mini
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: o1-mini
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/o3-mini
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: o3-mini
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_OPENAI:=__disabled__}/o4-mini
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: o4-mini
model_type: llm
- metadata:
embedding_dimension: 1536
context_length: 8192
model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-small
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: openai/text-embedding-3-small
model_type: embedding
- metadata:
embedding_dimension: 3072
context_length: 8192
model_id: ${env.ENABLE_OPENAI:=__disabled__}/openai/text-embedding-3-large
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: openai/text-embedding-3-large
model_type: embedding
- metadata:
embedding_dimension: 1536
context_length: 8192
model_id: ${env.ENABLE_OPENAI:=__disabled__}/text-embedding-3-small
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: text-embedding-3-small
model_type: embedding
- metadata:
embedding_dimension: 3072
context_length: 8192
model_id: ${env.ENABLE_OPENAI:=__disabled__}/text-embedding-3-large
provider_id: ${env.ENABLE_OPENAI:=__disabled__}
provider_model_id: text-embedding-3-large
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/claude-3-5-sonnet-latest
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/claude-3-5-sonnet-latest
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/claude-3-7-sonnet-latest
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/claude-3-7-sonnet-latest
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/claude-3-5-haiku-latest
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/claude-3-5-haiku-latest
model_type: llm
- metadata:
embedding_dimension: 1024
context_length: 32000
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/voyage-3
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/voyage-3
model_type: embedding
- metadata:
embedding_dimension: 512
context_length: 32000
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/voyage-3-lite
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/voyage-3-lite
model_type: embedding
- metadata:
embedding_dimension: 1024
context_length: 32000
model_id: ${env.ENABLE_ANTHROPIC:=__disabled__}/anthropic/voyage-code-3
provider_id: ${env.ENABLE_ANTHROPIC:=__disabled__}
provider_model_id: anthropic/voyage-code-3
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/gemini-1.5-flash
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/gemini-1.5-flash
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/gemini-1.5-pro
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/gemini-1.5-pro
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/gemini-2.0-flash
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/gemini-2.0-flash
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/gemini-2.5-flash
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/gemini-2.5-flash
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/gemini-2.5-pro
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/gemini-2.5-pro
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 2048
model_id: ${env.ENABLE_GEMINI:=__disabled__}/gemini/text-embedding-004
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/text-embedding-004
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama3-8b-8192
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama-3.1-8b-instant
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-3.1-8b-instant
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama3-70b-8192
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-3-70B-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama-3.3-70b-versatile
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama-3.2-3b-preview
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-3.2-3b-preview
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-3.2-3b-preview
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama-4-scout-17b-16e-instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/meta-llama/llama-4-scout-17b-16e-instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama-4-maverick-17b-128e-instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/meta-llama/llama-4-maverick-17b-128e-instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.1-8B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-3.1-405B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-3.2-1B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.2-1B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.2-3B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.3-70B-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Llama-3.2-11B-Vision-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Llama-3.2-90B-Vision-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/sambanova/Meta-Llama-Guard-3-8B
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_SAMBANOVA:=__disabled__}/meta-llama/Llama-Guard-3-8B
provider_id: ${env.ENABLE_SAMBANOVA:=__disabled__}
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=__disabled__}
provider_shield_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.SAFETY_MODEL:=__disabled__}
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