Merge-related changes.

2025-12-31 07:13:53 +00:00 · 2025-03-11 17:05:13 +01:00 · 2025-03-11 17:05:13 +01:00 · a714bbac9d
commit a714bbac9d
parent 8ca56484dc ead9397e22
95 changed files with 11044 additions and 4639 deletions
--- a/llama_stack/templates/ollama/build.yaml
+++ b/llama_stack/templates/ollama/build.yaml
@ -5,7 +5,7 @@ distribution_spec:
    inference:
    - remote::ollama
    vector_io:
-    - inline::sqlite-vec
+    - inline::faiss
    - remote::chromadb
    - remote::pgvector
    safety:
--- a/llama_stack/templates/ollama/doc_template.md
+++ b/llama_stack/templates/ollama/doc_template.md
@ -119,7 +119,7 @@ llama stack run ./run-with-safety.yaml \
 ### (Optional) Update Model Serving Configuration

 ```{note}
-Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/ollama.py#L45) for the supported Ollama models.
+Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/models.py) for the supported Ollama models.
 ```

 To serve a new model with `ollama`
--- a/llama_stack/templates/ollama/ollama.py
+++ b/llama_stack/templates/ollama/ollama.py
@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import (
    ShieldInput,
    ToolGroupInput,
 )
-from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings

@ -22,7 +22,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
    providers = {
        "inference": ["remote::ollama"],
-        "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
        "telemetry": ["inline::meta-reference"],
@ -45,10 +45,10 @@ def get_distribution_template() -> DistributionTemplate:
        provider_type="remote::ollama",
        config=OllamaImplConfig.sample_run_config(),
    )
-    vector_io_provider_sqlite = Provider(
-        provider_id="sqlite-vec",
-        provider_type="inline::sqlite-vec",
-        config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    vector_io_provider_faiss = Provider(
+        provider_id="faiss",
+        provider_type="inline::faiss",
+        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
    )

    inference_model = ModelInput(
@ -108,7 +108,7 @@ def get_distribution_template() -> DistributionTemplate:
            "run.yaml": RunConfigSettings(
                provider_overrides={
                    "inference": [inference_provider],
-                    "vector_io": [vector_io_provider_sqlite],
+                    "vector_io": [vector_io_provider_faiss],
                },
                default_models=[inference_model, embedding_model],
                default_tool_groups=default_tool_groups,
@ -117,7 +117,7 @@ def get_distribution_template() -> DistributionTemplate:
            "run-with-safety.yaml": RunConfigSettings(
                provider_overrides={
                    "inference": [inference_provider],
-                    "vector_io": [vector_io_provider_sqlite],
+                    "vector_io": [vector_io_provider_faiss],
                    "safety": [
                        Provider(
                            provider_id="llama-guard",
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@ -18,10 +18,13 @@ providers:
    config:
      url: ${env.OLLAMA_URL:http://localhost:11434}
  vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
+  - provider_id: faiss
+    provider_type: inline::faiss
    config:
-      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@ -18,10 +18,13 @@ providers:
    config:
      url: ${env.OLLAMA_URL:http://localhost:11434}
  vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
+  - provider_id: faiss
+    provider_type: inline::faiss
    config:
-      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
--- a/llama_stack/templates/open-benchmark/build.yaml
+++ b/llama_stack/templates/open-benchmark/build.yaml
@ -0,0 +1,36 @@
+version: '2'
+distribution_spec:
+  description: Distribution for running open benchmarks
+  providers:
+    inference:
+    - remote::openai
+    - remote::anthropic
+    - remote::gemini
+    - remote::groq
+    - remote::together
+    vector_io:
+    - inline::sqlite-vec
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+    eval:
+    - inline::meta-reference
+    datasetio:
+    - remote::huggingface
+    - inline::localfs
+    scoring:
+    - inline::basic
+    - inline::llm-as-judge
+    - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::rag-runtime
+    - remote::model-context-protocol
+image_type: conda
--- a/llama_stack/templates/open-benchmark/run.yaml
+++ b/llama_stack/templates/open-benchmark/run.yaml
@ -0,0 +1,230 @@
+version: '2'
+image_name: open-benchmark
+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: anthropic
+    provider_type: remote::anthropic
+    config:
+      api_key: ${env.ANTHROPIC_API_KEY:}
+  - provider_id: gemini
+    provider_type: remote::gemini
+    config:
+      api_key: ${env.GEMINI_API_KEY:}
+  - provider_id: groq
+    provider_type: remote::groq
+    config:
+      url: https://api.groq.com
+      api_key: ${env.GROQ_API_KEY:}
+  - provider_id: together
+    provider_type: remote::together
+    config:
+      url: https://api.together.xyz/v1
+      api_key: ${env.TOGETHER_API_KEY:}
+  vector_io:
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
+    config:
+      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/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: {}
+  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/dev}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dev/trace_store.db}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config: {}
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config: {}
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config: {}
+  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: code-interpreter
+    provider_type: inline::code-interpreter
+    config: {}
+  - 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/dev}/registry.db
+models:
+- metadata: {}
+  model_id: openai/gpt-4o
+  provider_id: openai
+  provider_model_id: openai/gpt-4o
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: anthropic/claude-3-5-sonnet-latest
+  provider_id: anthropic
+  provider_model_id: anthropic/claude-3-5-sonnet-latest
+  model_type: llm
+- metadata: {}
+  model_id: gemini/gemini-1.5-flash
+  provider_id: gemini
+  provider_model_id: gemini/gemini-1.5-flash
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
+shields:
+- shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
+datasets:
+  - dataset_id: simpleqa
+    provider_id: huggingface
+    url:
+      uri: https://huggingface.co/datasets/llamastack/simpleqa
+    metadata:
+      path: llamastack/simpleqa
+      name:
+      split: train
+    dataset_schema:
+      input_query:
+        type: string
+      expected_answer:
+        type: string
+      chat_completion_input:
+        type: string
+  - dataset_id: mmlu_cot
+    provider_id: huggingface
+    url:
+      uri: https://huggingface.co/datasets/llamastack/mmlu_cot
+    metadata:
+      path: llamastack/mmlu_cot
+      name: all
+      split: test
+    dataset_schema:
+      input_query:
+        type: string
+      expected_answer:
+        type: string
+      chat_completion_input:
+        type: string
+  - dataset_id: gpqa_cot
+    provider_id: huggingface
+    url:
+      uri: https://huggingface.co/datasets/llamastack/gpqa_0shot_cot
+    metadata:
+      path: llamastack/gpqa_0shot_cot
+      name: gpqa_main
+      split: train
+    dataset_schema:
+      input_query:
+        type: string
+      expected_answer:
+        type: string
+      chat_completion_input:
+        type: string
+  - dataset_id: math_500
+    provider_id: huggingface
+    url:
+      uri: https://huggingface.co/datasets/llamastack/math_500
+    metadata:
+      path: llamastack/math_500
+      name:
+      split: test
+    dataset_schema:
+      input_query:
+        type: string
+      expected_answer:
+        type: string
+      chat_completion_input:
+        type: string
+scoring_fns: []
+benchmarks:
+  - benchmark_id: meta-reference-simpleqa
+    dataset_id: simpleqa
+    scoring_functions: ["llm-as-judge::405b-simpleqa"]
+  - benchmark_id: meta-reference-mmlu-cot
+    dataset_id: mmlu_cot
+    scoring_functions: ["basic::regex_parser_multiple_choice_answer"]
+  - benchmark_id: meta-reference-gpqa-cot
+    dataset_id: gpqa_cot
+    scoring_functions: ["basic::regex_parser_multiple_choice_answer"]
+  - benchmark_id: meta-reference-math-500
+    dataset_id: math_500
+    scoring_functions: ["basic::regex_parser_math_response"]
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
+server:
+  port: 8321
--- a/llama_stack/templates/vllm-gpu/run.yaml
+++ b/llama_stack/templates/vllm-gpu/run.yaml
@ -16,11 +16,12 @@ providers:
  - provider_id: vllm
    provider_type: inline::vllm
    config:
-      model: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
      tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:1}
      max_tokens: ${env.MAX_TOKENS:4096}
+      max_model_len: ${env.MAX_MODEL_LEN:4096}
+      max_num_seqs: ${env.MAX_NUM_SEQS:4}
      enforce_eager: ${env.ENFORCE_EAGER:False}
-      gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.7}
+      gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.3}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}