Merge branch 'main' into vectordb_name

2025-12-24 02:08:02 +00:00 · 2025-07-09 20:53:46 -04:00 · 2025-07-09 20:53:46 -04:00 · 36ca9543a5
commit 36ca9543a5
parent 42ce6b96fc 7915551eee
35 changed files with 2282 additions and 1644 deletions
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@ -11132,8 +11132,38 @@
                "title": "Trace"
            },
            "Checkpoint": {
-                "description": "Checkpoint created during training runs",
-                "title": "Checkpoint"
+                "type": "object",
+                "properties": {
+                    "identifier": {
+                        "type": "string"
+                    },
+                    "created_at": {
+                        "type": "string",
+                        "format": "date-time"
+                    },
+                    "epoch": {
+                        "type": "integer"
+                    },
+                    "post_training_job_id": {
+                        "type": "string"
+                    },
+                    "path": {
+                        "type": "string"
+                    },
+                    "training_metrics": {
+                        "$ref": "#/components/schemas/PostTrainingMetric"
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "identifier",
+                    "created_at",
+                    "epoch",
+                    "post_training_job_id",
+                    "path"
+                ],
+                "title": "Checkpoint",
+                "description": "Checkpoint created during training runs"
            },
            "PostTrainingJobArtifactsResponse": {
                "type": "object",
@ -11156,6 +11186,31 @@
                "title": "PostTrainingJobArtifactsResponse",
                "description": "Artifacts of a finetuning job."
            },
+            "PostTrainingMetric": {
+                "type": "object",
+                "properties": {
+                    "epoch": {
+                        "type": "integer"
+                    },
+                    "train_loss": {
+                        "type": "number"
+                    },
+                    "validation_loss": {
+                        "type": "number"
+                    },
+                    "perplexity": {
+                        "type": "number"
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "epoch",
+                    "train_loss",
+                    "validation_loss",
+                    "perplexity"
+                ],
+                "title": "PostTrainingMetric"
+            },
            "PostTrainingJobStatusResponse": {
                "type": "object",
                "properties": {
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@ -7838,8 +7838,30 @@ components:
        - start_time
      title: Trace
    Checkpoint:
-      description: Checkpoint created during training runs
+      type: object
+      properties:
+        identifier:
+          type: string
+        created_at:
+          type: string
+          format: date-time
+        epoch:
+          type: integer
+        post_training_job_id:
+          type: string
+        path:
+          type: string
+        training_metrics:
+          $ref: '#/components/schemas/PostTrainingMetric'
+      additionalProperties: false
+      required:
+        - identifier
+        - created_at
+        - epoch
+        - post_training_job_id
+        - path
      title: Checkpoint
+      description: Checkpoint created during training runs
    PostTrainingJobArtifactsResponse:
      type: object
      properties:
@ -7855,6 +7877,24 @@ components:
        - checkpoints
      title: PostTrainingJobArtifactsResponse
      description: Artifacts of a finetuning job.
+    PostTrainingMetric:
+      type: object
+      properties:
+        epoch:
+          type: integer
+        train_loss:
+          type: number
+        validation_loss:
+          type: number
+        perplexity:
+          type: number
+      additionalProperties: false
+      required:
+        - epoch
+        - train_loss
+        - validation_loss
+        - perplexity
+      title: PostTrainingMetric
    PostTrainingJobStatusResponse:
      type: object
      properties:
--- a/docs/source/distributions/ondevice_distro/android_sdk.md
+++ b/docs/source/distributions/ondevice_distro/android_sdk.md
@ -13,7 +13,7 @@ Latest Release Notes: [link](https://github.com/meta-llama/llama-stack-client-ko
 *Tagged releases are stable versions of the project. While we strive to maintain a stable main branch, it's not guaranteed to be free of bugs or issues.*

 ## Android Demo App
-Check out our demo app to see how to integrate Llama Stack into your Android app: [Android Demo App](https://github.com/meta-llama/llama-stack-client-kotlin/tree/examples/android_app)
+Check out our demo app to see how to integrate Llama Stack into your Android app: [Android Demo App](https://github.com/meta-llama/llama-stack-client-kotlin/tree/latest-release/examples/android_app)

 The key files in the app are `ExampleLlamaStackLocalInference.kt`, `ExampleLlamaStackRemoteInference.kts`, and `MainActivity.java`. With encompassed business logic, the app shows how to use Llama Stack for both the environments.

@ -68,7 +68,7 @@ Ensure the Llama Stack server version is the same as the Kotlin SDK Library for

 Other inference providers: [Table](https://llama-stack.readthedocs.io/en/latest/index.html#supported-llama-stack-implementations)

-How to set remote localhost in Demo App: [Settings](https://github.com/meta-llama/llama-stack-apps/tree/main/examples/android_app#settings)
+How to set remote localhost in Demo App: [Settings](https://github.com/meta-llama/llama-stack-client-kotlin/tree/latest-release/examples/android_app#settings)

 ### Initialize the Client
 A client serves as the primary interface for interacting with a specific inference type and its associated parameters. Only after client is initialized then you can configure and start inferences.
@ -135,7 +135,7 @@ val result = client!!.inference().chatCompletionStreaming(

 ### Setup Custom Tool Calling

-Android demo app for more details: [Custom Tool Calling](https://github.com/meta-llama/llama-stack-apps/tree/main/examples/android_app#tool-calling)
+Android demo app for more details: [Custom Tool Calling](https://github.com/meta-llama/llama-stack-client-kotlin/tree/latest-release/examples/android_app#tool-calling)

 ## Advanced Users

--- a/docs/source/providers/vector_io/remote_milvus.md
+++ b/docs/source/providers/vector_io/remote_milvus.md
@ -114,6 +114,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
 | `uri` | `<class 'str'>` | No | PydanticUndefined | The URI of the Milvus server |
 | `token` | `str \| None` | No | PydanticUndefined | The token of the Milvus server |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
 | `config` | `dict` | No | {} | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |

 > **Note**: This configuration class accepts additional fields beyond those listed above. You can pass any additional configuration options that will be forwarded to the underlying provider.