phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions
llama-stack/llama_stack/templates/sambanova/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

211 lines
6.4 KiB
YAML
Raw Blame History

version: '2'
image_name: sambanova
apis:
- agents
- inference
- safety
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY}
- 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/sambanova}/faiss_store.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: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY}
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/sambanova}/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/sambanova}/trace_store.db
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: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/inference_store.db
models:
- 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: meta-llama/Llama-Guard-3-8B
provider_id: sambanova
provider_model_id: sambanova/Meta-Llama-Guard-3-8B
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
provider_shield_id: sambanova/Meta-Llama-Guard-3-8B
- shield_id: sambanova/Meta-Llama-Guard-3-8B
provider_shield_id: sambanova/Meta-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
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321
View git blame Copy permalink