phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into elasticsearch-integration

Browse source
This commit is contained in:
Enrico Zimuel 2025-11-20 14:42:18 +01:00 • committed by GitHub
commit 64124bc599
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
117 changed files with 16294 additions and 769 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

21
src/llama_stack/distributions/ci-tests/run.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

3
src/llama_stack/distributions/nvidia/run-with-safety.yaml
View file

@ -16,9 +16,8 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: nvidia
provider_type: remote::nvidia
config:

3
src/llama_stack/distributions/nvidia/run.yaml
View file

@ -16,9 +16,8 @@ providers:
- provider_id: nvidia
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
vector_io:
- provider_id: faiss
provider_type: inline::faiss

4
src/llama_stack/distributions/open-benchmark/run.yaml
View file

@ -27,12 +27,12 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: together
provider_type: remote::together
config:
url: https://api.together.xyz/v1
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
vector_io:
- provider_id: sqlite-vec

2
src/llama_stack/distributions/postgres-demo/run.yaml
View file

@ -11,7 +11,7 @@ providers:
- provider_id: vllm-inference
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=http://localhost:8000/v1}
base_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}

21
src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

21
src/llama_stack/distributions/starter-gpu/run.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

21
src/llama_stack/distributions/starter/run-with-postgres-store.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

21
src/llama_stack/distributions/starter/run.yaml
View file

@ -17,32 +17,32 @@ providers:
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
base_url: https://api.cerebras.ai/v1
api_key: ${env.CEREBRAS_API_KEY:=}
- provider_id: ${env.OLLAMA_URL:+ollama}
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
- provider_id: ${env.VLLM_URL:+vllm}
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=}
base_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.TGI_URL:+tgi}
provider_type: remote::tgi
config:
url: ${env.TGI_URL:=}
base_url: ${env.TGI_URL:=}
- provider_id: fireworks
provider_type: remote::fireworks
config:
url: https://api.fireworks.ai/inference/v1
base_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
base_url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY:=}
- provider_id: bedrock
provider_type: remote::bedrock
@ -52,9 +52,8 @@ providers:
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
provider_type: remote::nvidia
config:
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: openai
provider_type: remote::openai
config:
@ -76,18 +75,18 @@ providers:
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
base_url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
base_url: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers

2
src/llama_stack/distributions/watsonx/run.yaml
View file

@ -15,7 +15,7 @@ providers:
- provider_id: watsonx
provider_type: remote::watsonx
config:
url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
base_url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
api_key: ${env.WATSONX_API_KEY:=}
project_id: ${env.WATSONX_PROJECT_ID:=}
vector_io: