phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/llama_stack/templates/verification/run.yaml
ehhuang 549812f51e
feat: implement get chat completions APIs (#2200) 
# What does this PR do?
* Provide sqlite implementation of the APIs introduced in
https://github.com/meta-llama/llama-stack/pull/2145.
* Introduced a SqlStore API: llama_stack/providers/utils/sqlstore/api.py
and the first Sqlite implementation
* Pagination support will be added in a future PR.

## Test Plan
Unit test on sql store:
<img width="1005" alt="image"
src="https://github.com/user-attachments/assets/9b8b7ec8-632b-4667-8127-5583426b2e29"
/>


Integration test:
```
INFERENCE_MODEL="llama3.2:3b-instruct-fp16" llama stack build --template ollama --image-type conda --run
```
```
LLAMA_STACK_CONFIG=http://localhost:5001 INFERENCE_MODEL="llama3.2:3b-instruct-fp16" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-fp16" -k 'inference_store and openai'
```
2025-05-21 22:21:52 -07:00

728 lines
24 KiB
YAML
Raw Blame History

version: '2'
image_name: verification
apis:
- agents
- datasetio
- eval
- 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-openai-compat
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: together-openai-compat
provider_type: remote::together-openai-compat
config:
openai_compat_api_base: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: groq-openai-compat
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: sambanova-openai-compat
provider_type: remote::sambanova-openai-compat
config:
openai_compat_api_base: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:}
- provider_id: cerebras-openai-compat
provider_type: remote::cerebras-openai-compat
config:
openai_compat_api_base: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
vector_io:
- provider_id: sqlite-vec
provider_type: inline::sqlite-vec
config:
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/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:}
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/verification}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/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/verification}/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/verification}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/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/verification}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/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: gpt-3.5-turbo-0125
provider_id: openai
provider_model_id: gpt-3.5-turbo-0125
model_type: llm
- metadata: {}
model_id: gpt-3.5-turbo
provider_id: openai
provider_model_id: gpt-3.5-turbo
model_type: llm
- metadata: {}
model_id: gpt-3.5-turbo-instruct
provider_id: openai
provider_model_id: gpt-3.5-turbo-instruct
model_type: llm
- metadata: {}
model_id: gpt-4
provider_id: openai
provider_model_id: gpt-4
model_type: llm
- metadata: {}
model_id: gpt-4-turbo
provider_id: openai
provider_model_id: gpt-4-turbo
model_type: llm
- metadata: {}
model_id: gpt-4o
provider_id: openai
provider_model_id: gpt-4o
model_type: llm
- metadata: {}
model_id: gpt-4o-2024-08-06
provider_id: openai
provider_model_id: gpt-4o-2024-08-06
model_type: llm
- metadata: {}
model_id: gpt-4o-mini
provider_id: openai
provider_model_id: gpt-4o-mini
model_type: llm
- metadata: {}
model_id: gpt-4o-audio-preview
provider_id: openai
provider_model_id: gpt-4o-audio-preview
model_type: llm
- metadata: {}
model_id: chatgpt-4o-latest
provider_id: openai
provider_model_id: chatgpt-4o-latest
model_type: llm
- metadata: {}
model_id: o1
provider_id: openai
provider_model_id: o1
model_type: llm
- metadata: {}
model_id: o1-mini
provider_id: openai
provider_model_id: o1-mini
model_type: llm
- metadata: {}
model_id: o3-mini
provider_id: openai
provider_model_id: o3-mini
model_type: llm
- metadata: {}
model_id: 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: 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: 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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-guard-3-8b
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-11B-Vision
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: fireworks-openai-compat
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-openai-compat
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: fireworks-openai-compat
provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192
model_id: nomic-ai/nomic-embed-text-v1.5
provider_id: fireworks-openai-compat
provider_model_id: nomic-ai/nomic-embed-text-v1.5
model_type: embedding
- metadata: {}
model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Meta-Llama-Guard-3-8B
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: together-openai-compat
provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-11B-Vision
provider_id: together-openai-compat
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-openai-compat
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-openai-compat
provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
model_type: embedding
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together-openai-compat
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-openai-compat
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: together-openai-compat
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-openai-compat
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: groq/llama3-8b-8192
provider_id: groq-openai-compat
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: groq-openai-compat
provider_model_id: groq/llama3-8b-8192
model_type: llm
- metadata: {}
model_id: groq/llama-3.1-8b-instant
provider_id: groq-openai-compat
provider_model_id: groq/llama-3.1-8b-instant
model_type: llm
- metadata: {}
model_id: groq/llama3-70b-8192
provider_id: groq-openai-compat
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3-70B-Instruct
provider_id: groq-openai-compat
provider_model_id: groq/llama3-70b-8192
model_type: llm
- metadata: {}
model_id: groq/llama-3.3-70b-versatile
provider_id: groq-openai-compat
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: groq-openai-compat
provider_model_id: groq/llama-3.3-70b-versatile
model_type: llm
- metadata: {}
model_id: groq/llama-3.2-3b-preview
provider_id: groq-openai-compat
provider_model_id: groq/llama-3.2-3b-preview
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: groq-openai-compat
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-openai-compat
provider_model_id: groq/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: groq-openai-compat
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-openai-compat
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: groq-openai-compat
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-openai-compat
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: groq-openai-compat
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-openai-compat
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: groq-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: sambanova-openai-compat
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-openai-compat
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: sambanova-openai-compat
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: llama3.1-8b
provider_id: cerebras-openai-compat
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: cerebras-openai-compat
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: llama-3.3-70b
provider_id: cerebras-openai-compat
provider_model_id: llama-3.3-70b
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: cerebras-openai-compat
provider_model_id: llama-3.3-70b
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