release: 0.3.0-alpha.1

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.2.23-alpha.1"
+  ".": "0.3.0-alpha.1"
 }

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-f252873ea1e1f38fd207331ef2621c511154d5be3f4076e59cc15754fc58eee4.yml
-openapi_spec_hash: 10cbb4337a06a9fdd7d08612dd6044c3
-config_hash: 0358112cc0f3d880b4d55debdbe1cfa3
+configured_endpoints: 105
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-d7bea816190382a93511491e33d1f37f707620926ab133ae8ce0883d763df741.yml
+openapi_spec_hash: f73b3af77108625edae3f25972b9e665
+config_hash: 548f336ac1b68ab1dfe385b79df764dd

CHANGELOG.md

@@ -1,5 +1,36 @@
 # Changelog
 
+## 0.3.0-alpha.1 (2025-09-30)
+
+Full Changelog: [v0.2.23-alpha.1...v0.3.0-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.2.23-alpha.1...v0.3.0-alpha.1)
+
+### ⚠ BREAKING CHANGES
+
+* **api:** fixes to remove deprecated inference resources
+
+### Features
+
+* **api:** expires_after changes for /files ([7f24c43](https://github.com/llamastack/llama-stack-client-python/commit/7f24c432dc1859312710a4a1ff4a80f6f861bee8))
+* **api:** fixes to remove deprecated inference resources ([04834d2](https://github.com/llamastack/llama-stack-client-python/commit/04834d2189ae4e4b8cd2c9370d1d39857bc6e9ec))
+* **api:** removing openai/v1 ([a918b43](https://github.com/llamastack/llama-stack-client-python/commit/a918b4323118c18f77c2abe7e1a3054c1eebeaac))
+* **api:** updating post /v1/files to have correct multipart/form-data ([433a996](https://github.com/llamastack/llama-stack-client-python/commit/433a996527bcca131ada4730376d8993f34ad6f5))
+
+
+### Bug Fixes
+
+* clean up deprecated code ([f10ead0](https://github.com/llamastack/llama-stack-client-python/commit/f10ead00522b7ca803cd7dc3617da0d451efa7da))
+* Don't retry for non-recoverable server http errors ([#212](https://github.com/llamastack/llama-stack-client-python/issues/212)) ([6782e8f](https://github.com/llamastack/llama-stack-client-python/commit/6782e8fc5931369223ed4446f8e7732f62712eff))
+
+
+### Documentation
+
+* update examples ([f896747](https://github.com/llamastack/llama-stack-client-python/commit/f89674726f55915a8cda0e2b4284be3c92978121))
+
+
+### Build System
+
+* Bump version to 0.2.23 ([0d4dc64](https://github.com/llamastack/llama-stack-client-python/commit/0d4dc6449224fa2a0f6d20f6229dd9d1a5427861))
+
 ## 0.2.23-alpha.1 (2025-09-26)
 
 Full Changelog: [v0.2.19-alpha.1...v0.2.23-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.2.19-alpha.1...v0.2.23-alpha.1)

README.md

@@ -109,6 +109,50 @@ asyncio.run(main())
 
 Functionality between the synchronous and asynchronous clients is otherwise identical.
 
+## Streaming responses
+
+We provide support for streaming responses using Server Side Events (SSE).
+
+```python
+from llama_stack_client import LlamaStackClient
+
+client = LlamaStackClient()
+
+stream = client.chat.completions.create(
+    messages=[
+        {
+            "content": "string",
+            "role": "user",
+        }
+    ],
+    model="model",
+    stream=True,
+)
+for completion in stream:
+    print(completion)
+```
+
+The async client uses the exact same interface.
+
+```python
+from llama_stack_client import AsyncLlamaStackClient
+
+client = AsyncLlamaStackClient()
+
+stream = await client.chat.completions.create(
+    messages=[
+        {
+            "content": "string",
+            "role": "user",
+        }
+    ],
+    model="model",
+    stream=True,
+)
+async for completion in stream:
+    print(completion)
+```
+
 ## Using types
 
 Nested request parameters are [TypedDicts](https://docs.python.org/3/library/typing.html#typing.TypedDict). Responses are [Pydantic models](https://docs.pydantic.dev) which also provide helper methods for things like:
@@ -118,6 +162,40 @@ Nested request parameters are [TypedDicts](https://docs.python.org/3/library/typ
 
 Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set `python.analysis.typeCheckingMode` to `basic`.
 
+## Nested params
+
+Nested parameters are dictionaries, typed using `TypedDict`, for example:
+
+```python
+from llama_stack_client import LlamaStackClient
+
+client = LlamaStackClient()
+
+client.toolgroups.register(
+    provider_id="provider_id",
+    toolgroup_id="toolgroup_id",
+    mcp_endpoint={"uri": "uri"},
+)
+```
+
+## File uploads
+
+Request parameters that correspond to file uploads can be passed as `bytes`, or a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance or a tuple of `(filename, contents, media type)`.
+
+```python
+from pathlib import Path
+from llama_stack_client import LlamaStackClient
+
+client = LlamaStackClient()
+
+client.files.create(
+    file=Path("/path/to/file"),
+    purpose="assistants",
+)
+```
+
+The async client uses the exact same interface. If you pass a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance, the file contents will be read asynchronously automatically.
+
 ## Handling errors
 
 When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of `llama_stack_client.APIConnectionError` is raised.
@@ -134,9 +212,14 @@ from llama_stack_client import LlamaStackClient
 client = LlamaStackClient()
 
 try:
-    client.agents.sessions.create(
-        agent_id="agent_id",
-        session_name="session_name",
+    client.chat.completions.create(
+        messages=[
+            {
+                "content": "string",
+                "role": "user",
+            }
+        ],
+        model="model",
     )
 except llama_stack_client.APIConnectionError as e:
     print("The server could not be reached")
@@ -180,9 +263,14 @@ client = LlamaStackClient(
 )
 
 # Or, configure per-request:
-client.with_options(max_retries=5).agents.sessions.create(
-    agent_id="agent_id",
-    session_name="session_name",
+client.with_options(max_retries=5).chat.completions.create(
+    messages=[
+        {
+            "content": "string",
+            "role": "user",
+        }
+    ],
+    model="model",
 )
 ```
 
@@ -206,9 +294,14 @@ client = LlamaStackClient(
 )
 
 # Override per-request:
-client.with_options(timeout=5.0).agents.sessions.create(
-    agent_id="agent_id",
-    session_name="session_name",
+client.with_options(timeout=5.0).chat.completions.create(
+    messages=[
+        {
+            "content": "string",
+            "role": "user",
+        }
+    ],
+    model="model",
 )
 ```
 
@@ -248,14 +341,17 @@ The "raw" Response object can be accessed by prefixing `.with_raw_response.` to
 from llama_stack_client import LlamaStackClient
 
 client = LlamaStackClient()
-response = client.agents.sessions.with_raw_response.create(
-    agent_id="agent_id",
-    session_name="session_name",
+response = client.chat.completions.with_raw_response.create(
+    messages=[{
+        "content": "string",
+        "role": "user",
+    }],
+    model="model",
 )
 print(response.headers.get('X-My-Header'))
 
-session = response.parse()  # get the object that `agents.sessions.create()` would have returned
-print(session.session_id)
+completion = response.parse()  # get the object that `chat.completions.create()` would have returned
+print(completion)
 ```
 
 These methods return an [`APIResponse`](https://github.com/meta-llama/llama-stack-python/tree/main/src/llama_stack_client/_response.py) object.
@@ -269,9 +365,14 @@ 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.agents.sessions.with_streaming_response.create(
-    agent_id="agent_id",
-    session_name="session_name",
+with client.chat.completions.with_streaming_response.create(
+    messages=[
+        {
+            "content": "string",
+            "role": "user",
+        }
+    ],
+    model="model",
 ) as response:
     print(response.headers.get("X-My-Header"))