sync repo

meta-llama · Sep 17, 2024 · f567252 · f567252
1 parent 8acf430
commit f567252
Show file tree

Hide file tree

Showing 122 changed files with 4,675 additions and 7,737 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -31,13 +31,13 @@ $ pip install -r requirements-dev.lock
 
 ## Modifying/Adding code
 
-Most of the SDK is generated code, and any modified code will be overridden on the next generation. The
-`src/llama_stack/lib/` and `examples/` directories are exceptions and will never be overridden.
+Most of the SDK is generated code. Modifications to code will be persisted between generations, but may
+result in merge conflicts between manual patches and changes from the generator. The generator will never
+modify the contents of the `src/llama_stack/lib/` and `examples/` directories.
 
 ## Adding and running examples
 
-All files in the `examples/` directory are not modified by the Stainless generator and can be freely edited or
-added to.
+All files in the `examples/` directory are not modified by the generator and can be freely edited or added to.
 
 ```bash
 # add an example to examples/<your-example>.py

diff --git a/README.md b/README.md
@@ -15,7 +15,8 @@ The REST API documentation can be found on [docs.llama-stack.todo](https://docs.
 ## Installation
 
 ```sh
-pip install llama-stack
+# install from this staging repo
+pip install llama-stack-client
 ```
 
 ## Usage
@@ -30,13 +31,11 @@ client = LlamaStack(
     environment="sandbox",
 )
 
-agentic_system_create_response = client.agentic_system.create(
-    agent_config={
-        "instructions": "instructions",
-        "model": "model",
-    },
+session = client.agentic_system.sessions.create(
+    agent_id="agent_id",
+    session_name="session_name",
 )
-print(agentic_system_create_response.agent_id)
+print(session.session_id)
 ```
 
 ## Async usage
@@ -54,13 +53,11 @@ client = AsyncLlamaStack(
 
 
 async def main() -> None:
-    agentic_system_create_response = await client.agentic_system.create(
-        agent_config={
-            "instructions": "instructions",
-            "model": "model",
-        },
+    session = await client.agentic_system.sessions.create(
+        agent_id="agent_id",
+        session_name="session_name",
     )
-    print(agentic_system_create_response.agent_id)
+    print(session.session_id)
 
 
 asyncio.run(main())
@@ -93,11 +90,9 @@ from llama_stack import LlamaStack
 client = LlamaStack()
 
 try:
-    client.agentic_system.create(
-        agent_config={
-            "instructions": "instructions",
-            "model": "model",
-        },
+    client.agentic_system.sessions.create(
+        agent_id="agent_id",
+        session_name="session_name",
     )
 except llama_stack.APIConnectionError as e:
     print("The server could not be reached")
@@ -141,11 +136,9 @@ client = LlamaStack(
 )
 
 # Or, configure per-request:
-client.with_options(max_retries=5).agentic_system.create(
-    agent_config={
-        "instructions": "instructions",
-        "model": "model",
-    },
+client.with_options(max_retries=5).agentic_system.sessions.create(
+    agent_id="agent_id",
+    session_name="session_name",
 )
 ```
 
@@ -169,11 +162,9 @@ client = LlamaStack(
 )
 
 # Override per-request:
-client.with_options(timeout=5.0).agentic_system.create(
-    agent_config={
-        "instructions": "instructions",
-        "model": "model",
-    },
+client.with_options(timeout=5.0).agentic_system.sessions.create(
+    agent_id="agent_id",
+    session_name="session_name",
 )
 ```
 
@@ -213,16 +204,14 @@ The "raw" Response object can be accessed by prefixing `.with_raw_response.` to
 from llama_stack import LlamaStack
 
 client = LlamaStack()
-response = client.agentic_system.with_raw_response.create(
-    agent_config={
-        "instructions": "instructions",
-        "model": "model",
-    },
+response = client.agentic_system.sessions.with_raw_response.create(
+    agent_id="agent_id",
+    session_name="session_name",
 )
 print(response.headers.get('X-My-Header'))
 
-agentic_system = response.parse()  # get the object that `agentic_system.create()` would have returned
-print(agentic_system.agent_id)
+session = response.parse()  # get the object that `agentic_system.sessions.create()` would have returned
+print(session.session_id)
 ```
 
 These methods return an [`APIResponse`](https://github.com/stainless-sdks/llama-stack-python/tree/main/src/llama_stack/_response.py) object.
@@ -236,11 +225,9 @@ The above interface eagerly reads the full response body when you make the reque
 To stream the response body, use `.with_streaming_response` instead, which requires a context manager and only reads the response body once you call `.read()`, `.text()`, `.json()`, `.iter_bytes()`, `.iter_text()`, `.iter_lines()` or `.parse()`. In the async client, these are async methods.
 
 ```python
-with client.agentic_system.with_streaming_response.create(
-    agent_config={
-        "instructions": "instructions",
-        "model": "model",
-    },
+with client.agentic_system.sessions.with_streaming_response.create(
+    agent_id="agent_id",
+    session_name="session_name",
 ) as response:
     print(response.headers.get("X-My-Header"))
 

diff --git a/api.md b/api.md
@@ -2,11 +2,9 @@
 
 ```python
 from llama_stack.types import (
-    Artifact,
     Attachment,
     BatchCompletion,
     CompletionMessage,
-    Run,
     SamplingParams,
     SystemMessage,
     ToolCall,
@@ -15,13 +13,29 @@ from llama_stack.types import (
 )
 ```
 
+# Telemetry
+
+Types:
+
+```python
+from llama_stack.types import TelemetryGetTraceResponse
+```
+
+Methods:
+
+- <code title="get /telemetry/get_trace">client.telemetry.<a href="./src/llama_stack/resources/telemetry.py">get_trace</a>(\*\*<a href="src/llama_stack/types/telemetry_get_trace_params.py">params</a>) -> <a href="./src/llama_stack/types/telemetry_get_trace_response.py">TelemetryGetTraceResponse</a></code>
+- <code title="post /telemetry/log_event">client.telemetry.<a href="./src/llama_stack/resources/telemetry.py">log</a>(\*\*<a href="src/llama_stack/types/telemetry_log_params.py">params</a>) -> None</code>
+
 # AgenticSystem
 
 Types:
 
 ```python
 from llama_stack.types import (
+    CustomQueryGeneratorConfig,
+    DefaultQueryGeneratorConfig,
     InferenceStep,
+    LlmQueryGeneratorConfig,
     MemoryRetrievalStep,
     RestAPIExecutionConfig,
     ShieldCallStep,
@@ -68,20 +82,14 @@ Methods:
 Types:
 
 ```python
-from llama_stack.types.agentic_system import AgenticSystemTurnStreamChunk, Turn
+from llama_stack.types.agentic_system import AgenticSystemTurnStreamChunk, Turn, TurnStreamEvent
 ```
 
 Methods:
 
 - <code title="post /agentic_system/turn/create">client.agentic_system.turns.<a href="./src/llama_stack/resources/agentic_system/turns.py">create</a>(\*\*<a href="src/llama_stack/types/agentic_system/turn_create_params.py">params</a>) -> <a href="./src/llama_stack/types/agentic_system/agentic_system_turn_stream_chunk.py">AgenticSystemTurnStreamChunk</a></code>
 - <code title="get /agentic_system/turn/get">client.agentic_system.turns.<a href="./src/llama_stack/resources/agentic_system/turns.py">retrieve</a>(\*\*<a href="src/llama_stack/types/agentic_system/turn_retrieve_params.py">params</a>) -> <a href="./src/llama_stack/types/agentic_system/turn.py">Turn</a></code>
 
-# Artifacts
-
-Methods:
-
-- <code title="get /artifacts/get">client.artifacts.<a href="./src/llama_stack/resources/artifacts.py">get</a>(\*\*<a href="src/llama_stack/types/artifact_get_params.py">params</a>) -> <a href="./src/llama_stack/types/shared/artifact.py">Artifact</a></code>
-
 # Datasets
 
 Types:
@@ -152,41 +160,24 @@ Methods:
 - <code title="post /evaluate/summarization/">client.evaluations.<a href="./src/llama_stack/resources/evaluations.py">summarization</a>(\*\*<a href="src/llama_stack/types/evaluation_summarization_params.py">params</a>) -> <a href="./src/llama_stack/types/evaluation_job.py">EvaluationJob</a></code>
 - <code title="post /evaluate/text_generation/">client.evaluations.<a href="./src/llama_stack/resources/evaluations.py">text_generation</a>(\*\*<a href="src/llama_stack/types/evaluation_text_generation_params.py">params</a>) -> <a href="./src/llama_stack/types/evaluation_job.py">EvaluationJob</a></code>
 
-# Experiments
-
-Types:
-
-```python
-from llama_stack.types import Experiment
-```
-
-Methods:
-
-- <code title="post /experiments/create">client.experiments.<a href="./src/llama_stack/resources/experiments/experiments.py">create</a>(\*\*<a href="src/llama_stack/types/experiment_create_params.py">params</a>) -> <a href="./src/llama_stack/types/experiment.py">Experiment</a></code>
-- <code title="get /experiments/get">client.experiments.<a href="./src/llama_stack/resources/experiments/experiments.py">retrieve</a>(\*\*<a href="src/llama_stack/types/experiment_retrieve_params.py">params</a>) -> <a href="./src/llama_stack/types/experiment.py">Experiment</a></code>
-- <code title="post /experiments/update">client.experiments.<a href="./src/llama_stack/resources/experiments/experiments.py">update</a>(\*\*<a href="src/llama_stack/types/experiment_update_params.py">params</a>) -> <a href="./src/llama_stack/types/experiment.py">Experiment</a></code>
-- <code title="get /experiments/list">client.experiments.<a href="./src/llama_stack/resources/experiments/experiments.py">list</a>() -> <a href="./src/llama_stack/types/experiment.py">Experiment</a></code>
-- <code title="post /experiments/create_run">client.experiments.<a href="./src/llama_stack/resources/experiments/experiments.py">create_run</a>(\*\*<a href="src/llama_stack/types/experiment_create_run_params.py">params</a>) -> <a href="./src/llama_stack/types/shared/run.py">Run</a></code>
-
-## Artifacts
-
-Methods:
-
-- <code title="post /experiments/artifacts/get">client.experiments.artifacts.<a href="./src/llama_stack/resources/experiments/artifacts.py">retrieve</a>(\*\*<a href="src/llama_stack/types/experiments/artifact_retrieve_params.py">params</a>) -> <a href="./src/llama_stack/types/shared/artifact.py">Artifact</a></code>
-- <code title="post /experiments/artifacts/upload">client.experiments.artifacts.<a href="./src/llama_stack/resources/experiments/artifacts.py">upload</a>(\*\*<a href="src/llama_stack/types/experiments/artifact_upload_params.py">params</a>) -> <a href="./src/llama_stack/types/shared/artifact.py">Artifact</a></code>
-
 # Inference
 
 Types:
 
 ```python
-from llama_stack.types import ChatCompletionStreamChunk, CompletionStreamChunk
+from llama_stack.types import (
+    ChatCompletionStreamChunk,
+    CompletionStreamChunk,
+    TokenLogProbs,
+    InferenceChatCompletionResponse,
+    InferenceCompletionResponse,
+)
 ```
 
 Methods:
 
-- <code title="post /inference/chat_completion">client.inference.<a href="./src/llama_stack/resources/inference/inference.py">chat_completion</a>(\*\*<a href="src/llama_stack/types/inference_chat_completion_params.py">params</a>) -> <a href="./src/llama_stack/types/chat_completion_stream_chunk.py">ChatCompletionStreamChunk</a></code>
-- <code title="post /inference/completion">client.inference.<a href="./src/llama_stack/resources/inference/inference.py">completion</a>(\*\*<a href="src/llama_stack/types/inference_completion_params.py">params</a>) -> <a href="./src/llama_stack/types/completion_stream_chunk.py">CompletionStreamChunk</a></code>
+- <code title="post /inference/chat_completion">client.inference.<a href="./src/llama_stack/resources/inference/inference.py">chat_completion</a>(\*\*<a href="src/llama_stack/types/inference_chat_completion_params.py">params</a>) -> <a href="./src/llama_stack/types/inference_chat_completion_response.py">InferenceChatCompletionResponse</a></code>
+- <code title="post /inference/completion">client.inference.<a href="./src/llama_stack/resources/inference/inference.py">completion</a>(\*\*<a href="src/llama_stack/types/inference_completion_params.py">params</a>) -> <a href="./src/llama_stack/types/inference_completion_response.py">InferenceCompletionResponse</a></code>
 
 ## Embeddings
 
@@ -200,19 +191,6 @@ Methods:
 
 - <code title="post /inference/embeddings">client.inference.embeddings.<a href="./src/llama_stack/resources/inference/embeddings.py">create</a>(\*\*<a href="src/llama_stack/types/inference/embedding_create_params.py">params</a>) -> <a href="./src/llama_stack/types/inference/embeddings.py">Embeddings</a></code>
 
-# Logging
-
-Types:
-
-```python
-from llama_stack.types import LoggingGetLogsResponse
-```
-
-Methods:
-
-- <code title="post /logging/get_logs">client.logging.<a href="./src/llama_stack/resources/logging.py">get_logs</a>(\*\*<a href="src/llama_stack/types/logging_get_logs_params.py">params</a>) -> <a href="./src/llama_stack/types/logging_get_logs_response.py">LoggingGetLogsResponse</a></code>
-- <code title="post /logging/log_messages">client.logging.<a href="./src/llama_stack/resources/logging.py">log_messages</a>(\*\*<a href="src/llama_stack/types/logging_log_messages_params.py">params</a>) -> None</code>
-
 # Safety
 
 Types:
@@ -307,25 +285,6 @@ Methods:
 
 - <code title="post /reward_scoring/score">client.reward_scoring.<a href="./src/llama_stack/resources/reward_scoring.py">score</a>(\*\*<a href="src/llama_stack/types/reward_scoring_score_params.py">params</a>) -> <a href="./src/llama_stack/types/reward_scoring.py">RewardScoring</a></code>
 
-# Runs
-
-Methods:
-
-- <code title="post /runs/update">client.runs.<a href="./src/llama_stack/resources/runs/runs.py">update</a>(\*\*<a href="src/llama_stack/types/run_update_params.py">params</a>) -> <a href="./src/llama_stack/types/shared/run.py">Run</a></code>
-- <code title="post /runs/log_metrics">client.runs.<a href="./src/llama_stack/resources/runs/runs.py">log_metrics</a>(\*\*<a href="src/llama_stack/types/run_log_metrics_params.py">params</a>) -> None</code>
-
-## Metrics
-
-Types:
-
-```python
-from llama_stack.types.runs import MetricListResponse
-```
-
-Methods:
-
-- <code title="get /runs/metrics">client.runs.metrics.<a href="./src/llama_stack/resources/runs/metrics.py">list</a>(\*\*<a href="src/llama_stack/types/runs/metric_list_params.py">params</a>) -> <a href="./src/llama_stack/types/runs/metric_list_response.py">MetricListResponse</a></code>
-
 # SyntheticDataGeneration
 
 Types:

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
-name = "llama_stack"
-version = "0.0.1-alpha.4"
+name = "llama_stack_client"
+version = "0.0.1-alpha.0"
 description = "The official Python library for the llama-stack API"
 dynamic = ["readme"]
 license = "Apache-2.0"

diff --git a/requirements-dev.lock b/requirements-dev.lock
@@ -49,7 +49,7 @@ markdown-it-py==3.0.0
     # via rich
 mdurl==0.1.2
     # via markdown-it-py
-mypy==1.10.1
+mypy==1.11.2
 mypy-extensions==1.0.0
     # via mypy
 nodeenv==1.8.0
@@ -70,7 +70,7 @@ pydantic-core==2.18.2
     # via pydantic
 pygments==2.18.0
     # via rich
-pyright==1.1.374
+pyright==1.1.380
 pytest==7.1.1
     # via pytest-asyncio
 pytest-asyncio==0.21.1
@@ -80,7 +80,7 @@ pytz==2023.3.post1
     # via dirty-equals
 respx==0.20.2
 rich==13.7.1
-ruff==0.5.6
+ruff==0.6.5
 setuptools==68.2.2
     # via nodeenv
 six==1.16.0