Skip to content

Upgrade llama-stack from v0.6.0 to v0.7.1 #2104

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
anik120 wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

Upgrade llama-stack from v0.6.0 to v0.7.1 #2104

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e1ba0fe
Upgrade llama-stack from v0.6.0 to v0.7.1
anik120 Jul 9, 2026
2ef8a02
Update providers submodule to llama-stack v0.7.1 compatibility
anik120 Jul 9, 2026
bc17208
Refactor code for llama-stack v0.7.1 API compatibility
anik120 Jul 9, 2026
7046dce
Fix runtime compatibility with llama-stack v0.7.1 Responses API
anik120 Jul 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2,828 changes: 2,579 additions & 249 deletions .konflux/requirements.hashes.source.txt
View file
Open in desktop

Large diffs are not rendered by default.

22 changes: 12 additions & 10 deletions examples/azure-run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ version: 2
image_name: azure-configuration

apis:
- agents
- responses
- batches
- datasetio
- eval
Expand All @@ -11,6 +11,8 @@ apis:
- safety
- scoring
- tool_runtime
- tool_groups
- conversations
- vector_io

benchmarks: []
Expand Down Expand Up @@ -51,8 +53,8 @@ providers:
provider_type: inline::basic
tool_runtime:
- config: {} # Enable the RAG tool
provider_id: rag-runtime
provider_type: inline::rag-runtime
provider_id: file-search
provider_type: inline::file-search
- config: {} # Enable MCP (Model Context Protocol) support
provider_id: model-context-protocol
provider_type: remote::model-context-protocol
Expand All @@ -63,7 +65,7 @@ providers:
backend: kv_rag
provider_id: faiss
provider_type: inline::faiss
agents:
responses:
- config:
persistence:
agent_state:
Expand All @@ -72,8 +74,8 @@ providers:
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
batches:
- config:
kvstore:
Expand All @@ -99,8 +101,8 @@ providers:
kvstore:
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
scoring_fns: []
server:
port: 8321
Expand Down Expand Up @@ -155,8 +157,8 @@ registered_resources:
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::file_search
provider_id: file-search
vector_stores:
default_provider_id: faiss
default_embedding_model:
Expand Down
22 changes: 12 additions & 10 deletions examples/bedrock-run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
version: 2

apis:
- agents
- responses
- batches
- datasetio
- eval
Expand All @@ -10,6 +10,8 @@ apis:
- safety
- scoring
- tool_runtime
- tool_groups
- conversations
- vector_io

benchmarks: []
Expand Down Expand Up @@ -57,8 +59,8 @@ providers:
openai_api_key: '********'
tool_runtime:
- config: {} # Enable the RAG tool
provider_id: rag-runtime
provider_type: inline::rag-runtime
provider_id: file-search
provider_type: inline::file-search
- config: {} # Enable MCP (Model Context Protocol) support
provider_id: model-context-protocol
provider_type: remote::model-context-protocol
Expand All @@ -69,7 +71,7 @@ providers:
backend: kv_default
provider_id: faiss
provider_type: inline::faiss
agents:
responses:
- config:
persistence:
agent_state:
Expand All @@ -78,8 +80,8 @@ providers:
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
batches:
- config:
kvstore:
Expand All @@ -105,8 +107,8 @@ providers:
kvstore:
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
scoring_fns: []
server:
port: 8321
Expand Down Expand Up @@ -154,8 +156,8 @@ registered_resources:
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag # Register the RAG tool
provider_id: rag-runtime
- toolgroup_id: builtin::file_search # Register the RAG tool
provider_id: file-search
vector_stores:
default_provider_id: faiss
default_embedding_model:
Expand Down
22 changes: 12 additions & 10 deletions examples/run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
version: 2

apis:
- agents
- responses
- batches
- datasetio
- eval
Expand All @@ -16,6 +16,8 @@ apis:
- safety
- scoring
- tool_runtime
- tool_groups
- conversations
- vector_io

benchmarks: []
Expand Down Expand Up @@ -59,12 +61,12 @@ providers:
openai_api_key: '********'
tool_runtime:
- config: {} # Enable the RAG tool
provider_id: rag-runtime
provider_type: inline::rag-runtime
provider_id: file-search
provider_type: inline::file-search
- config: {} # Enable the MCP tool
provider_id: model-context-protocol
provider_type: remote::model-context-protocol
agents:
responses:
- config:
persistence:
agent_state:
Expand All @@ -73,8 +75,8 @@ providers:
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
batches:
- config:
kvstore:
Expand All @@ -100,8 +102,8 @@ providers:
kvstore:
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
scoring_fns: []
server:
port: 8321
Expand Down Expand Up @@ -142,8 +144,8 @@ registered_resources:
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag # Register the RAG tool
provider_id: rag-runtime
- toolgroup_id: builtin::file_search # Register the RAG tool
provider_id: file-search
vector_stores:
annotation_prompt_params: # Override the default Llama Stack annotation that adds <| file-xyz |> to responses
enable_annotations: true
Expand Down
22 changes: 12 additions & 10 deletions examples/vertexai-run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ version: 2
image_name: vertexai-configuration

apis:
- agents
- responses
- batches
- datasetio
- eval
Expand All @@ -11,6 +11,8 @@ apis:
- safety
- scoring
- tool_runtime
- tool_groups
- conversations
- vector_io

benchmarks: []
Expand Down Expand Up @@ -51,8 +53,8 @@ providers:
provider_type: inline::basic
tool_runtime:
- config: {} # Enable the RAG tool
provider_id: rag-runtime
provider_type: inline::rag-runtime
provider_id: file-search
provider_type: inline::file-search
- config: {} # Enable MCP (Model Context Protocol) support
provider_id: model-context-protocol
provider_type: remote::model-context-protocol
Expand All @@ -63,7 +65,7 @@ providers:
backend: kv_rag
provider_id: faiss
provider_type: inline::faiss
agents:
responses:
- config:
persistence:
agent_state:
Expand All @@ -72,8 +74,8 @@ providers:
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
batches:
- config:
kvstore:
Expand All @@ -99,8 +101,8 @@ providers:
kvstore:
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
scoring_fns: []
server:
port: 8321
Expand Down Expand Up @@ -151,8 +153,8 @@ registered_resources:
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::file_search
provider_id: file-search
vector_stores:
default_provider_id: faiss
default_embedding_model:
Expand Down
22 changes: 12 additions & 10 deletions examples/watsonx-run.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
version: 2

apis:
- agents
- responses
- batches
- datasetio
- eval
Expand All @@ -10,6 +10,8 @@ apis:
- safety
- scoring
- tool_runtime
- tool_groups
- conversations
- vector_io

benchmarks: []
Expand Down Expand Up @@ -59,8 +61,8 @@ providers:
openai_api_key: '********'
tool_runtime:
- config: {} # Enable the RAG tool
provider_id: rag-runtime
provider_type: inline::rag-runtime
provider_id: file-search
provider_type: inline::file-search
- config: {} # Enable MCP (Model Context Protocol) support
provider_id: model-context-protocol
provider_type: remote::model-context-protocol
Expand All @@ -71,7 +73,7 @@ providers:
backend: kv_rag
provider_id: faiss
provider_type: inline::faiss
agents:
responses:
- config:
persistence:
agent_state:
Expand All @@ -80,8 +82,8 @@ providers:
responses:
table_name: agents_responses
backend: sql_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
batches:
- config:
kvstore:
Expand All @@ -107,8 +109,8 @@ providers:
kvstore:
namespace: eval_store
backend: kv_default
provider_id: meta-reference
provider_type: inline::meta-reference
provider_id: builtin
provider_type: inline::builtin
scoring_fns: []
server:
port: 8321
Expand Down Expand Up @@ -163,8 +165,8 @@ registered_resources:
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag # Register the RAG tool
provider_id: rag-runtime
- toolgroup_id: builtin::file_search # Register the RAG tool
provider_id: file-search
vector_stores:
default_provider_id: faiss
default_embedding_model: # Define the default embedding model for RAG
Expand Down
2 changes: 1 addition & 1 deletion providers
Open in desktop
Submodule providers updated from 9ab872 to 537fab
6 changes: 3 additions & 3 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,9 @@ dependencies = [
# Used by authentication/k8s integration
"kubernetes>=30.1.0",
# Used to call Llama Stack APIs
"llama-stack==0.6.0",
"llama-stack-client==0.6.0",
"llama-stack-api==0.6.0",
"llama-stack==0.7.1",
"llama-stack-client==0.7.1",
"llama-stack-api==0.7.1",
# Used by Logger
"rich>=14.0.0",
# Used by JWK token auth handler
Expand Down
Loading
Loading