fix!: update eval-tasks -> benchmarks

docs/getting_started.ipynb

@@ -324,7 +324,7 @@
               "- vector_io\n",
               "container_image: null\n",
               "datasets: <span style=\"font-weight: bold\">[]</span>\n",
-              "eval_tasks: <span style=\"font-weight: bold\">[]</span>\n",
+              "benchmarks: <span style=\"font-weight: bold\">[]</span>\n",
               "image_name: together\n",
               "metadata_store:\n",
               "  db_path: <span style=\"color: #800080; text-decoration-color: #800080\">/Users/ashwin/.llama/distributions/together/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">registry.db</span>\n",
@@ -508,7 +508,7 @@
               "- vector_io\n",
               "container_image: null\n",
               "datasets: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
-              "eval_tasks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+              "benchmarks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
               "image_name: together\n",
               "metadata_store:\n",
               "  db_path: \u001b[35m/Users/ashwin/.llama/distributions/together/\u001b[0m\u001b[95mregistry.db\u001b[0m\n",

docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb

@@ -370,7 +370,7 @@
               "- tool_runtime\n",
               "datasets: <span style=\"font-weight: bold\">[]</span>\n",
               "container_image: null\n",
-              "eval_tasks: <span style=\"font-weight: bold\">[]</span>\n",
+              "benchmarks: <span style=\"font-weight: bold\">[]</span>\n",
               "image_name: together\n",
               "memory_banks: <span style=\"font-weight: bold\">[]</span>\n",
               "metadata_store:\n",
@@ -551,7 +551,7 @@
               "- tool_runtime\n",
               "datasets: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
               "container_image: null\n",
-              "eval_tasks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+              "benchmarks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
               "image_name: together\n",
               "memory_banks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
               "metadata_store:\n",

docs/openapi_generator/pyopenapi/generator.py

@@ -647,6 +647,7 @@ def _build_operation(self, op: EndpointOperation) -> Operation:
         description = "\n".join(
             filter(None, [doc_string.short_description, doc_string.long_description])
         )
+
         return Operation(
             tags=[op.defining_class.__name__],
             summary=None,
@@ -656,6 +657,7 @@ def _build_operation(self, op: EndpointOperation) -> Operation:
             requestBody=requestBody,
             responses=responses,
             callbacks=callbacks,
+            deprecated=True if "DEPRECATED" in op.func_name else None,
             security=[] if op.public else None,
         )
 

docs/openapi_generator/pyopenapi/specification.py

@@ -117,6 +117,7 @@ class Operation:
     requestBody: Optional[RequestBody] = None
     callbacks: Optional[Dict[str, "Callback"]] = None
     security: Optional[List["SecurityRequirement"]] = None
+    deprecated: Optional[bool] = None
 
 
 @dataclass

docs/source/building_applications/evals.md

@@ -41,14 +41,14 @@ system_message = {
     "content": SYSTEM_PROMPT_TEMPLATE,
 }
 
-client.eval_tasks.register(
-    eval_task_id="meta-reference::mmmu",
+client.benchmarks.register(
+    benchmark_id="meta-reference::mmmu",
     dataset_id=f"mmmu-{subset}-{split}",
     scoring_functions=["basic::regex_parser_multiple_choice_answer"],
 )
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::mmmu",
+    benchmark_id="meta-reference::mmmu",
     input_rows=eval_rows,
     scoring_functions=["basic::regex_parser_multiple_choice_answer"],
     task_config={
@@ -99,14 +99,14 @@ eval_rows = client.datasetio.get_rows_paginated(
 ```
 
 ```python
-client.eval_tasks.register(
-    eval_task_id="meta-reference::simpleqa",
+client.benchmarks.register(
+    benchmark_id="meta-reference::simpleqa",
     dataset_id=simpleqa_dataset_id,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
 )
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::simpleqa",
+    benchmark_id="meta-reference::simpleqa",
     input_rows=eval_rows.rows,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
     task_config={
@@ -156,7 +156,7 @@ agent_config = {
 }
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::simpleqa",
+    benchmark_id="meta-reference::simpleqa",
     input_rows=eval_rows.rows,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
     task_config={

docs/source/building_applications/evaluation.md

@@ -10,21 +10,21 @@ Here's how to set up basic evaluation:
 
 ```python
 # Create an evaluation task
-response = client.eval_tasks.register(
-    eval_task_id="my_eval",
+response = client.benchmarks.register(
+    benchmark_id="my_eval",
     dataset_id="my_dataset",
     scoring_functions=["accuracy", "relevance"],
 )
 
 # Run evaluation
 job = client.eval.run_eval(
-    task_id="my_eval",
+    benchmark_id="my_eval",
     task_config={
         "type": "app",
         "eval_candidate": {"type": "agent", "config": agent_config},
     },
 )
 
 # Get results
-result = client.eval.job_result(task_id="my_eval", job_id=job.job_id)
+result = client.eval.job_result(benchmark_id="my_eval", job_id=job.job_id)
 ```

docs/source/concepts/evaluation_concepts.md

@@ -5,7 +5,7 @@ The Llama Stack Evaluation flow allows you to run evaluations on your GenAI appl
 We introduce a set of APIs in Llama Stack for supporting running evaluations of LLM applications.
 - `/datasetio` + `/datasets` API
 - `/scoring` + `/scoring_functions` API
-- `/eval` + `/eval_tasks` API
+- `/eval` + `/benchmarks` API
 
 This guide goes over the sets of APIs and developer experience flow of using Llama Stack to run evaluations for different use cases. Checkout our Colab notebook on working examples with evaluations [here](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing).
 
@@ -21,7 +21,7 @@ The Evaluation APIs are associated with a set of Resources as shown in the follo
 - **Scoring**: evaluate outputs of the system.
   - Associated with `ScoringFunction` resource. We provide a suite of out-of-the box scoring functions and also the ability for you to add custom evaluators. These scoring functions are the core part of defining an evaluation task to output evaluation metrics.
 - **Eval**: generate outputs (via Inference or Agents) and perform scoring.
-  - Associated with `EvalTask` resource.
+  - Associated with `Benchmark` resource.
 
 
 Use the following decision tree to decide how to use LlamaStack Evaluation flow.

docs/source/concepts/index.md

@@ -42,7 +42,7 @@ Some of these APIs are associated with a set of **Resources**. Here is the mappi
 - **Tool Runtime** is associated with `ToolGroup` resources.
 - **DatasetIO** is associated with `Dataset` resources.
 - **Scoring** is associated with `ScoringFunction` resources.
-- **Eval** is associated with `Model` and `EvalTask` resources.
+- **Eval** is associated with `Model` and `Benchmark` resources.
 
 Furthermore, we allow these resources to be **federated** across multiple providers. For example, you may have some Llama models served by Fireworks while others are served by AWS Bedrock. Regardless, they will all work seamlessly with the same uniform Inference API provided by Llama Stack.
 

docs/source/playground/index.md

@@ -64,7 +64,7 @@ Interactive pages for users to play with and explore Llama Stack API capabilitie
     ```
 
     ```bash
-    $ llama-stack-client eval_tasks register \
+    $ llama-stack-client benchmarks register \
     --eval-task-id meta-reference-mmlu \
     --provider-id meta-reference \
     --dataset-id mmlu \
@@ -86,7 +86,7 @@ Interactive pages for users to play with and explore Llama Stack API capabilitie
   - Under the hood, it uses Llama Stack's `/providers` API to get information about the providers.
 
 - **API Resources**: Inspect Llama Stack API resources
-  - This page allows you to inspect Llama Stack API resources (`models`, `datasets`, `memory_banks`, `eval_tasks`, `shields`).
+  - This page allows you to inspect Llama Stack API resources (`models`, `datasets`, `memory_banks`, `benchmarks`, `shields`).
   - Under the hood, it uses Llama Stack's `/<resources>/list` API to get information about each resources.
   - Please visit [Core Concepts](https://llama-stack.readthedocs.io/en/latest/concepts/index.html) for more details about the resources.
 

docs/source/references/evals_reference/index.md

@@ -5,7 +5,7 @@ The Llama Stack Evaluation flow allows you to run evaluations on your GenAI appl
 We introduce a set of APIs in Llama Stack for supporting running evaluations of LLM applications.
 - `/datasetio` + `/datasets` API
 - `/scoring` + `/scoring_functions` API
-- `/eval` + `/eval_tasks` API
+- `/eval` + `/benchmarks` API
 
 This guide goes over the sets of APIs and developer experience flow of using Llama Stack to run evaluations for different use cases. Checkout our Colab notebook on working examples with evaluations [here](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing).
 
@@ -21,7 +21,7 @@ The Evaluation APIs are associated with a set of Resources as shown in the follo
 - **Scoring**: evaluate outputs of the system.
   - Associated with `ScoringFunction` resource. We provide a suite of out-of-the box scoring functions and also the ability for you to add custom evaluators. These scoring functions are the core part of defining an evaluation task to output evaluation metrics.
 - **Eval**: generate outputs (via Inference or Agents) and perform scoring.
-  - Associated with `EvalTask` resource.
+  - Associated with `Benchmark` resource.
 
 
 Use the following decision tree to decide how to use LlamaStack Evaluation flow.
@@ -77,14 +77,14 @@ system_message = {
     "content": SYSTEM_PROMPT_TEMPLATE,
 }
 
-client.eval_tasks.register(
-    eval_task_id="meta-reference::mmmu",
+client.benchmarks.register(
+    benchmark_id="meta-reference::mmmu",
     dataset_id=f"mmmu-{subset}-{split}",
     scoring_functions=["basic::regex_parser_multiple_choice_answer"],
 )
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::mmmu",
+    benchmark_id="meta-reference::mmmu",
     input_rows=eval_rows,
     scoring_functions=["basic::regex_parser_multiple_choice_answer"],
     task_config={
@@ -135,14 +135,14 @@ eval_rows = client.datasetio.get_rows_paginated(
 ```
 
 ```python
-client.eval_tasks.register(
-    eval_task_id="meta-reference::simpleqa",
+client.benchmarks.register(
+    benchmark_id="meta-reference::simpleqa",
     dataset_id=simpleqa_dataset_id,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
 )
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::simpleqa",
+    benchmark_id="meta-reference::simpleqa",
     input_rows=eval_rows.rows,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
     task_config={
@@ -192,7 +192,7 @@ agent_config = {
 }
 
 response = client.eval.evaluate_rows(
-    task_id="meta-reference::simpleqa",
+    benchmark_id="meta-reference::simpleqa",
     input_rows=eval_rows.rows,
     scoring_functions=["llm-as-judge::405b-simpleqa"],
     task_config={
@@ -281,15 +281,15 @@ The following examples give the quick steps to start running evaluations using t
 
 #### Benchmark Evaluation CLI
 Usage: There are 2 inputs necessary for running a benchmark eval
-- `eval-task-id`: the identifier associated with the eval task. Each `EvalTask` is parametrized by
+- `eval-task-id`: the identifier associated with the eval task. Each `Benchmark` is parametrized by
   - `dataset_id`: the identifier associated with the dataset.
   - `List[scoring_function_id]`: list of scoring function identifiers.
 - `eval-task-config`: specifies the configuration of the model / agent to evaluate on.
 
 
 ```
 llama-stack-client eval run_benchmark <eval-task-id> \
---eval-task-config ~/eval_task_config.json \
+--eval-task-config ~/benchmark_config.json \
 --visualize
 ```
 
@@ -309,15 +309,15 @@ llama-stack-client eval run_scoring <scoring_fn_id_1> <scoring_fn_id_2> ... <sco
 --output-dir ./
 ```
 
-#### Defining EvalTaskConfig
-The `EvalTaskConfig` are user specified config to define:
+#### Defining BenchmarkConfig
+The `BenchmarkConfig` are user specified config to define:
 1. `EvalCandidate` to run generation on:
    - `ModelCandidate`: The model will be used for generation through LlamaStack /inference API.
    - `AgentCandidate`: The agentic system specified by AgentConfig will be used for generation through LlamaStack  /agents API.
 2. Optionally scoring function params to allow customization of scoring function behaviour. This is useful to parameterize generic scoring functions such as LLMAsJudge with custom `judge_model` / `judge_prompt`.
 
 
-**Example Benchmark EvalTaskConfig**
+**Example Benchmark BenchmarkConfig**
 ```json
 {
     "type": "benchmark",
@@ -335,7 +335,7 @@ The `EvalTaskConfig` are user specified config to define:
 }
 ```
 
-**Example Application EvalTaskConfig**
+**Example Application BenchmarkConfig**
 ```json
 {
     "type": "app",

docs/source/references/llama_stack_client_cli_reference.md

@@ -161,14 +161,14 @@ Options:
 
 ## Eval Task Management
 
-### `llama-stack-client eval_tasks list`
+### `llama-stack-client benchmarks list`
 ```bash
-$ llama-stack-client eval_tasks list
+$ llama-stack-client benchmarks list
 ```
 
-### `llama-stack-client eval_tasks register`
+### `llama-stack-client benchmarks register`
 ```bash
-$ llama-stack-client eval_tasks register --eval-task-id <eval-task-id> --dataset-id <dataset-id> --scoring-functions <function1> [<function2> ...] [--provider-id <provider-id>] [--provider-eval-task-id <provider-eval-task-id>] [--metadata <metadata>]
+$ llama-stack-client benchmarks register --eval-task-id <eval-task-id> --dataset-id <dataset-id> --scoring-functions <function1> [<function2> ...] [--provider-id <provider-id>] [--provider-eval-task-id <provider-eval-task-id>] [--metadata <metadata>]
 ```
 
 Options:
@@ -191,7 +191,7 @@ Options:
 - `--num-examples`: Optional. Number of examples to evaluate (useful for debugging)
 - `--visualize`: Optional flag. If set, visualizes evaluation results after completion
 
-Example eval_task_config.json:
+Example benchmark_config.json:
 ```json
 {
     "type": "benchmark",

docs/source/references/python_sdk_reference/index.md

@@ -181,8 +181,8 @@ from llama_stack_client.types import EvaluateResponse, Job
 
 Methods:
 
-- <code title="post /v1/eval/tasks/{task_id}/evaluations">client.eval.<a href="./src/llama_stack_client/resources/eval/eval.py">evaluate_rows</a>(task_id, \*\*<a href="src/llama_stack_client/types/eval_evaluate_rows_params.py">params</a>) -> <a href="./src/llama_stack_client/types/evaluate_response.py">EvaluateResponse</a></code>
-- <code title="post /v1/eval/tasks/{task_id}/jobs">client.eval.<a href="./src/llama_stack_client/resources/eval/eval.py">run_eval</a>(task_id, \*\*<a href="src/llama_stack_client/types/eval_run_eval_params.py">params</a>) -> <a href="./src/llama_stack_client/types/job.py">Job</a></code>
+- <code title="post /v1/eval/tasks/{benchmark_id}/evaluations">client.eval.<a href="./src/llama_stack_client/resources/eval/eval.py">evaluate_rows</a>(benchmark_id, \*\*<a href="src/llama_stack_client/types/eval_evaluate_rows_params.py">params</a>) -> <a href="./src/llama_stack_client/types/evaluate_response.py">EvaluateResponse</a></code>
+- <code title="post /v1/eval/tasks/{benchmark_id}/jobs">client.eval.<a href="./src/llama_stack_client/resources/eval/eval.py">run_eval</a>(benchmark_id, \*\*<a href="src/llama_stack_client/types/eval_run_eval_params.py">params</a>) -> <a href="./src/llama_stack_client/types/job.py">Job</a></code>
 
 ### Jobs
 
@@ -194,9 +194,9 @@ from llama_stack_client.types.eval import JobStatusResponse
 
 Methods:
 
-- <code title="get /v1/eval/tasks/{task_id}/jobs/{job_id}/result">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">retrieve</a>(job_id, \*, task_id) -> <a href="./src/llama_stack_client/types/evaluate_response.py">EvaluateResponse</a></code>
-- <code title="delete /v1/eval/tasks/{task_id}/jobs/{job_id}">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">cancel</a>(job_id, \*, task_id) -> None</code>
-- <code title="get /v1/eval/tasks/{task_id}/jobs/{job_id}">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">status</a>(job_id, \*, task_id) -> Optional[JobStatusResponse]</code>
+- <code title="get /v1/eval/tasks/{benchmark_id}/jobs/{job_id}/result">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">retrieve</a>(job_id, \*, benchmark_id) -> <a href="./src/llama_stack_client/types/evaluate_response.py">EvaluateResponse</a></code>
+- <code title="delete /v1/eval/tasks/{benchmark_id}/jobs/{job_id}">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">cancel</a>(job_id, \*, benchmark_id) -> None</code>
+- <code title="get /v1/eval/tasks/{benchmark_id}/jobs/{job_id}">client.eval.jobs.<a href="./src/llama_stack_client/resources/eval/jobs.py">status</a>(job_id, \*, benchmark_id) -> Optional[JobStatusResponse]</code>
 
 ## Inspect
 
@@ -443,20 +443,20 @@ Methods:
 - <code title="get /v1/scoring-functions">client.scoring_functions.<a href="./src/llama_stack_client/resources/scoring_functions.py">list</a>() -> <a href="./src/llama_stack_client/types/scoring_function_list_response.py">ScoringFunctionListResponse</a></code>
 - <code title="post /v1/scoring-functions">client.scoring_functions.<a href="./src/llama_stack_client/resources/scoring_functions.py">register</a>(\*\*<a href="src/llama_stack_client/types/scoring_function_register_params.py">params</a>) -> None</code>
 
-## EvalTasks
+## Benchmarks
 
 Types:
 
 ```python
 from llama_stack_client.types import (
-    EvalTask,
-    ListEvalTasksResponse,
-    EvalTaskListResponse,
+    Benchmark,
+    ListBenchmarksResponse,
+    BenchmarkListResponse,
 )
 ```
 
 Methods:
 
-- <code title="get /v1/eval-tasks/{eval_task_id}">client.eval_tasks.<a href="./src/llama_stack_client/resources/eval_tasks.py">retrieve</a>(eval_task_id) -> <a href="./src/llama_stack_client/types/eval_task.py">Optional[EvalTask]</a></code>
-- <code title="get /v1/eval-tasks">client.eval_tasks.<a href="./src/llama_stack_client/resources/eval_tasks.py">list</a>() -> <a href="./src/llama_stack_client/types/eval_task_list_response.py">EvalTaskListResponse</a></code>
-- <code title="post /v1/eval-tasks">client.eval_tasks.<a href="./src/llama_stack_client/resources/eval_tasks.py">register</a>(\*\*<a href="src/llama_stack_client/types/eval_task_register_params.py">params</a>) -> None</code>
+- <code title="get /v1/eval-tasks/{benchmark_id}">client.benchmarks.<a href="./src/llama_stack_client/resources/benchmarks.py">retrieve</a>(benchmark_id) -> <a href="./src/llama_stack_client/types/benchmark.py">Optional[Benchmark]</a></code>
+- <code title="get /v1/eval-tasks">client.benchmarks.<a href="./src/llama_stack_client/resources/benchmarks.py">list</a>() -> <a href="./src/llama_stack_client/types/benchmark_list_response.py">BenchmarkListResponse</a></code>
+- <code title="post /v1/eval-tasks">client.benchmarks.<a href="./src/llama_stack_client/resources/benchmarks.py">register</a>(\*\*<a href="src/llama_stack_client/types/benchmark_register_params.py">params</a>) -> None</code>

llama_stack/apis/eval_tasks/__init__.py → llama_stack/apis/benchmarks/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .eval_tasks import *  # noqa: F401 F403
+from .benchmarks import *  # noqa: F401 F403