llama-stack-client 0.4.4 → 0.4.5

package/src/resources/shared.ts

@@ -6,6 +6,19 @@
 //
 // File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
+import * as ProvidersAPI from './providers';
+import * as RoutesAPI from './routes';
+
+/**
+ * Health status information for the service.
+ */
+export interface HealthInfo {
+  /**
+   * The health status of the service
+   */
+  status: 'OK' | 'Error' | 'Not Implemented';
+}
+
 /**
  * A image content item
  */
@@ -158,6 +171,26 @@ export namespace InterleavedContentItem {
   }
 }
 
+/**
+ * Response containing a list of all available providers.
+ */
+export interface ListProvidersResponse {
+  /**
+   * List of provider information objects
+   */
+  data: ProvidersAPI.ProviderListResponse;
+}
+
+/**
+ * Response containing a list of all available API routes.
+ */
+export interface ListRoutesResponse {
+  /**
+   * List of available API routes
+   */
+  data: RoutesAPI.RouteListResponse;
+}
+
 /**
  * Parameter type for string values.
  */
@@ -237,33 +270,102 @@ export namespace ParamType {
   }
 }
 
+/**
+ * Information about a registered provider including its configuration and health
+ * status.
+ */
+export interface ProviderInfo {
+  /**
+   * The API name this provider implements
+   */
+  api: string;
+
+  /**
+   * Configuration parameters for the provider
+   */
+  config: { [key: string]: unknown };
+
+  /**
+   * Current health status of the provider
+   */
+  health: { [key: string]: unknown };
+
+  /**
+   * Unique identifier for the provider
+   */
+  provider_id: string;
+
+  /**
+   * The type of provider implementation
+   */
+  provider_type: string;
+}
+
+/**
+ * Information about an API route including its path, method, and implementing
+ * providers.
+ */
+export interface RouteInfo {
+  /**
+   * The HTTP method for the route
+   */
+  method: string;
+
+  /**
+   * List of provider types implementing this route
+   */
+  provider_types: Array<string>;
+
+  /**
+   * The API route path
+   */
+  route: string;
+}
+
 /**
  * Details of a safety violation detected by content moderation.
  */
 export interface SafetyViolation {
   /**
-   * Severity level of a safety violation.
+   * Severity level of the violation
    */
   violation_level: 'info' | 'warn' | 'error';
 
+  /**
+   * Additional metadata including specific violation codes
+   */
   metadata?: { [key: string]: unknown };
 
+  /**
+   * Message to convey to the user about the violation
+   */
   user_message?: string | null;
 }
 
 /**
- * Sampling parameters.
+ * Sampling parameters for text generation.
  */
 export interface SamplingParams {
+  /**
+   * The maximum number of tokens that can be generated in the completion. The token
+   * count of your prompt plus max_tokens cannot exceed the model's context length.
+   */
   max_tokens?: number | null;
 
+  /**
+   * Number between -2.0 and 2.0. Positive values penalize new tokens based on
+   * whether they appear in the text so far.
+   */
   repetition_penalty?: number | null;
 
+  /**
+   * Up to 4 sequences where the API will stop generating further tokens. The
+   * returned text will not contain the stop sequence.
+   */
   stop?: Array<string> | null;
 
   /**
-   * Greedy sampling strategy that selects the highest probability token at each
-   * step.
+   * The sampling strategy to use.
    */
   strategy?:
     | SamplingParams.GreedySamplingStrategy
@@ -277,6 +379,9 @@ export namespace SamplingParams {
    * step.
    */
   export interface GreedySamplingStrategy {
+    /**
+     * Must be 'greedy' to identify this sampling strategy.
+     */
     type?: 'greedy';
   }
 
@@ -285,10 +390,19 @@ export namespace SamplingParams {
    * with cumulative probability >= p.
    */
   export interface TopPSamplingStrategy {
-    temperature: number | null;
+    /**
+     * Controls randomness in sampling. Higher values increase randomness.
+     */
+    temperature: number;
 
-    top_p?: number | null;
+    /**
+     * Cumulative probability threshold for nucleus sampling.
+     */
+    top_p?: number;
 
+    /**
+     * Must be 'top_p' to identify this sampling strategy.
+     */
     type?: 'top_p';
   }
 
@@ -296,8 +410,14 @@ export namespace SamplingParams {
    * Top-k sampling strategy that restricts sampling to the k most likely tokens.
    */
   export interface TopKSamplingStrategy {
+    /**
+     * Number of top tokens to consider for sampling. Must be at least 1.
+     */
     top_k: number;
 
+    /**
+     * Must be 'top_k' to identify this sampling strategy.
+     */
     type?: 'top_k';
   }
 }
@@ -306,8 +426,14 @@ export namespace SamplingParams {
  * A scoring result for a single row.
  */
 export interface ScoringResult {
+  /**
+   * Map of metric name to aggregated value
+   */
   aggregated_results: { [key: string]: unknown };
 
+  /**
+   * The scoring result for each row. Each row is a map of column name to value.
+   */
   score_rows: Array<{ [key: string]: unknown }>;
 }
 
@@ -316,7 +442,9 @@ export interface ScoringResult {
  */
 export interface SystemMessage {
   /**
-   * A image content item
+   * The content of the 'system prompt'. If multiple system messages are provided,
+   * they are concatenated. The underlying Llama Stack code may also add other system
+   * messages.
    */
   content:
     | string
@@ -324,6 +452,9 @@ export interface SystemMessage {
     | SystemMessage.TextContentItem
     | Array<SystemMessage.ImageContentItemInput | SystemMessage.TextContentItem>;
 
+  /**
+   * Must be 'system' to identify this as a system message.
+   */
   role?: 'system';
 }
 
@@ -416,3 +547,13 @@ export namespace SystemMessage {
     type?: 'text';
   }
 }
+
+/**
+ * Version information for the service.
+ */
+export interface VersionInfo {
+  /**
+   * The version string of the service
+   */
+  version: string;
+}

package/src/resources/shields.ts

@@ -48,7 +48,13 @@ export class Shields extends APIResource {
   }
 }
 
+/**
+ * Response containing a list of all shields.
+ */
 export interface ListShieldsResponse {
+  /**
+   * List of shield objects
+   */
   data: ShieldListResponse;
 }
 
@@ -76,15 +82,30 @@ export interface Shield {
   type?: 'shield';
 }
 
+/**
+ * List of shield objects
+ */
 export type ShieldListResponse = Array<Shield>;
 
 export interface ShieldRegisterParams {
+  /**
+   * The identifier of the shield to register.
+   */
   shield_id: string;
 
+  /**
+   * The parameters of the shield.
+   */
   params?: { [key: string]: unknown } | null;
 
+  /**
+   * The identifier of the provider.
+   */
   provider_id?: string | null;
 
+  /**
+   * The identifier of the shield in the provider.
+   */
   provider_shield_id?: string | null;
 }
 

package/src/resources/vector-io.ts

@@ -11,7 +11,7 @@ import * as Core from '../core';
 
 export class VectorIo extends APIResource {
   /**
-   * Insert chunks into a vector database.
+   * Insert embedded chunks into a vector database.
    */
   insert(body: VectorIoInsertParams, options?: Core.RequestOptions): Core.APIPromise<void> {
     return this._client.post('/v1/vector-io/insert', {
@@ -40,11 +40,22 @@ export interface QueryChunksResponse {
 
 export namespace QueryChunksResponse {
   /**
-   * A chunk of content that can be inserted into a vector database.
+   * A chunk of content with its embedding vector for vector database operations.
+   * Inherits all fields from Chunk and adds embedding-related fields.
    */
   export interface Chunk {
     chunk_id: string;
 
+    /**
+     * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
+     * additional information about the chunk that will not be used in the context
+     * during inference, but is required for backend functionality. The `ChunkMetadata`
+     * is set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not
+     * expected to change after. Use `Chunk.metadata` for metadata that will be used in
+     * the context during inference.
+     */
+    chunk_metadata: Chunk.ChunkMetadata;
+
     /**
      * A image content item
      */
@@ -54,6 +65,16 @@ export namespace QueryChunksResponse {
       | Chunk.TextContentItem
       | Array<Chunk.ImageContentItemOutput | Chunk.TextContentItem>;
 
+    embedding: Array<number>;
+
+    embedding_dimension: number;
+
+    embedding_model: string;
+
+    metadata?: { [key: string]: unknown };
+  }
+
+  export namespace Chunk {
     /**
      * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
      * additional information about the chunk that will not be used in the context
@@ -62,14 +83,26 @@ export namespace QueryChunksResponse {
      * expected to change after. Use `Chunk.metadata` for metadata that will be used in
      * the context during inference.
      */
-    chunk_metadata?: Chunk.ChunkMetadata | null;
+    export interface ChunkMetadata {
+      chunk_id?: string | null;
 
-    embedding?: Array<number> | null;
+      chunk_tokenizer?: string | null;
 
-    metadata?: { [key: string]: unknown };
-  }
+      chunk_window?: string | null;
+
+      content_token_count?: number | null;
+
+      created_timestamp?: number | null;
+
+      document_id?: string | null;
+
+      metadata_token_count?: number | null;
+
+      source?: string | null;
+
+      updated_timestamp?: number | null;
+    }
 
-  export namespace Chunk {
     /**
      * A image content item
      */
@@ -157,56 +190,44 @@ export namespace QueryChunksResponse {
 
       type?: 'text';
     }
-
-    /**
-     * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
-     * additional information about the chunk that will not be used in the context
-     * during inference, but is required for backend functionality. The `ChunkMetadata`
-     * is set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not
-     * expected to change after. Use `Chunk.metadata` for metadata that will be used in
-     * the context during inference.
-     */
-    export interface ChunkMetadata {
-      chunk_embedding_dimension?: number | null;
-
-      chunk_embedding_model?: string | null;
-
-      chunk_id?: string | null;
-
-      chunk_tokenizer?: string | null;
-
-      chunk_window?: string | null;
-
-      content_token_count?: number | null;
-
-      created_timestamp?: number | null;
-
-      document_id?: string | null;
-
-      metadata_token_count?: number | null;
-
-      source?: string | null;
-
-      updated_timestamp?: number | null;
-    }
   }
 }
 
 export interface VectorIoInsertParams {
+  /**
+   * The list of embedded chunks to insert.
+   */
   chunks: Array<VectorIoInsertParams.Chunk>;
 
+  /**
+   * The ID of the vector store to insert chunks into.
+   */
   vector_store_id: string;
 
+  /**
+   * Time-to-live in seconds for the inserted chunks.
+   */
   ttl_seconds?: number | null;
 }
 
 export namespace VectorIoInsertParams {
   /**
-   * A chunk of content that can be inserted into a vector database.
+   * A chunk of content with its embedding vector for vector database operations.
+   * Inherits all fields from Chunk and adds embedding-related fields.
    */
   export interface Chunk {
     chunk_id: string;
 
+    /**
+     * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
+     * additional information about the chunk that will not be used in the context
+     * during inference, but is required for backend functionality. The `ChunkMetadata`
+     * is set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not
+     * expected to change after. Use `Chunk.metadata` for metadata that will be used in
+     * the context during inference.
+     */
+    chunk_metadata: Chunk.ChunkMetadata;
+
     /**
      * A image content item
      */
@@ -216,6 +237,16 @@ export namespace VectorIoInsertParams {
       | Chunk.TextContentItem
       | Array<Chunk.ImageContentItemInput | Chunk.TextContentItem>;
 
+    embedding: Array<number>;
+
+    embedding_dimension: number;
+
+    embedding_model: string;
+
+    metadata?: { [key: string]: unknown };
+  }
+
+  export namespace Chunk {
     /**
      * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
      * additional information about the chunk that will not be used in the context
@@ -224,14 +255,26 @@ export namespace VectorIoInsertParams {
      * expected to change after. Use `Chunk.metadata` for metadata that will be used in
      * the context during inference.
      */
-    chunk_metadata?: Chunk.ChunkMetadata | null;
+    export interface ChunkMetadata {
+      chunk_id?: string | null;
 
-    embedding?: Array<number> | null;
+      chunk_tokenizer?: string | null;
 
-    metadata?: { [key: string]: unknown };
-  }
+      chunk_window?: string | null;
+
+      content_token_count?: number | null;
+
+      created_timestamp?: number | null;
+
+      document_id?: string | null;
+
+      metadata_token_count?: number | null;
+
+      source?: string | null;
+
+      updated_timestamp?: number | null;
+    }
 
-  export namespace Chunk {
     /**
      * A image content item
      */
@@ -319,44 +362,12 @@ export namespace VectorIoInsertParams {
 
       type?: 'text';
     }
-
-    /**
-     * `ChunkMetadata` is backend metadata for a `Chunk` that is used to store
-     * additional information about the chunk that will not be used in the context
-     * during inference, but is required for backend functionality. The `ChunkMetadata`
-     * is set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not
-     * expected to change after. Use `Chunk.metadata` for metadata that will be used in
-     * the context during inference.
-     */
-    export interface ChunkMetadata {
-      chunk_embedding_dimension?: number | null;
-
-      chunk_embedding_model?: string | null;
-
-      chunk_id?: string | null;
-
-      chunk_tokenizer?: string | null;
-
-      chunk_window?: string | null;
-
-      content_token_count?: number | null;
-
-      created_timestamp?: number | null;
-
-      document_id?: string | null;
-
-      metadata_token_count?: number | null;
-
-      source?: string | null;
-
-      updated_timestamp?: number | null;
-    }
   }
 }
 
 export interface VectorIoQueryParams {
   /**
-   * A image content item
+   * The query content to search for.
    */
   query:
     | string
@@ -364,8 +375,14 @@ export interface VectorIoQueryParams {
     | VectorIoQueryParams.TextContentItem
     | Array<VectorIoQueryParams.ImageContentItemInput | VectorIoQueryParams.TextContentItem>;
 
+  /**
+   * The ID of the vector store to query.
+   */
   vector_store_id: string;
 
+  /**
+   * Additional query parameters.
+   */
   params?: { [key: string]: unknown } | null;
 }
 

package/src/resources/vector-stores/file-batches.ts

@@ -15,10 +15,7 @@ import { type OpenAICursorPageParams } from '../../pagination';
 
 export class FileBatches extends APIResource {
   /**
-   * Create a vector store file batch.
-   *
-   * Generate an OpenAI-compatible vector store file batch for the given vector
-   * store.
+   * Create a vector store file batch (OpenAI-compatible).
    */
   create(
     vectorStoreId: string,
@@ -29,7 +26,7 @@ export class FileBatches extends APIResource {
   }
 
   /**
-   * Retrieve a vector store file batch.
+   * Retrieve a vector store file batch (OpenAI-compatible).
    */
   retrieve(
     vectorStoreId: string,
@@ -40,7 +37,7 @@ export class FileBatches extends APIResource {
   }
 
   /**
-   * Cancels a vector store file batch.
+   * Cancel a vector store file batch (OpenAI-compatible).
    */
   cancel(
     vectorStoreId: string,
@@ -51,7 +48,7 @@ export class FileBatches extends APIResource {
   }
 
   /**
-   * Returns a list of vector store files in a batch.
+   * List files in a vector store file batch (OpenAI-compatible).
    */
   listFiles(
     vectorStoreId: string,
@@ -182,10 +179,19 @@ export namespace FileBatchCreateParams {
 }
 
 export interface FileBatchListFilesParams extends OpenAICursorPageParams {
+  /**
+   * Pagination cursor (before).
+   */
   before?: string | null;
 
+  /**
+   * Filter by file status.
+   */
   filter?: string | null;
 
+  /**
+   * Sort order by created_at: asc or desc.
+   */
   order?: string | null;
 }