cohere-ai · billytrend-cohere · Oct 4, 2024 · Oct 4, 2024
diff --git a/package.json b/package.json
@@ -23,7 +23,8 @@
         "@aws-sdk/client-sagemaker": "^3.583.0",
         "@aws-sdk/credential-providers": "^3.583.0",
         "@aws-sdk/protocol-http": "^3.374.0",
-        "@aws-sdk/signature-v4": "^3.374.0"
+        "@aws-sdk/signature-v4": "^3.374.0",
+        "convict": "^6.2.4"
     },
     "devDependencies": {
         "@types/url-join": "4.0.1",
@@ -39,7 +40,8 @@
         "typescript": "4.6.4",
         "@types/readable-stream": "^4.0.14",
         "ts-loader": "^9.5.1",
-        "webpack": "^5.91.0"
+        "webpack": "^5.91.0",
+        "@types/convict": "^6.1.6"
     },
     "browser": {
         "fs": false,

diff --git a/reference.md b/reference.md
@@ -71,7 +71,9 @@ await client.checkApiKey();
 <dl>
 <dd>
 
-Generates a message from the model in response to a provided conversation. To learn how to use the Chat API with Streaming and RAG follow our Text Generation guides.
+Generates a message from the model in response to a provided conversation. To learn more about the features of the Chat API follow our [Text Generation guides](https://docs.cohere.com/v2/docs/chat-api).
+
+Follow the [Migration Guide](https://docs.cohere.com/v2/docs/migrating-v1-to-v2) for instructions on moving from API v1 to API v2.
 
 </dd>
 </dl>
@@ -173,7 +175,9 @@ await client.v2.chatStream({
 <dl>
 <dd>
 
-Generates a message from the model in response to a provided conversation. To learn how to use the Chat API with Streaming and RAG follow our Text Generation guides.
+Generates a message from the model in response to a provided conversation. To learn more about the features of the Chat API follow our [Text Generation guides](https://docs.cohere.com/v2/docs/chat-api).
+
+Follow the [Migration Guide](https://docs.cohere.com/v2/docs/migrating-v1-to-v2) for instructions on moving from API v1 to API v2.
 
 </dd>
 </dl>
@@ -266,6 +270,8 @@ If you want to learn more how to use the embedding model, have a look at the [Se
 ```typescript
 await client.v2.embed({
     model: "model",
+    inputType: Cohere.EmbedInputType.SearchDocument,
+    embeddingTypes: [Cohere.EmbeddingType.Float],
 });
 ```
 

diff --git a/src/api/resources/v2/client/Client.ts b/src/api/resources/v2/client/Client.ts
@@ -35,7 +35,9 @@ export class V2 {
     constructor(protected readonly _options: V2.Options = {}) {}
 
     /**
-     * Generates a message from the model in response to a provided conversation. To learn how to use the Chat API with Streaming and RAG follow our Text Generation guides.
+     * Generates a message from the model in response to a provided conversation. To learn more about the features of the Chat API follow our [Text Generation guides](https://docs.cohere.com/v2/docs/chat-api).
+     *
+     * Follow the [Migration Guide](https://docs.cohere.com/v2/docs/migrating-v1-to-v2) for instructions on moving from API v1 to API v2.
      */
     public async chatStream(
         request: Cohere.V2ChatStreamRequest,
@@ -183,7 +185,9 @@ export class V2 {
     }
 
     /**
-     * Generates a message from the model in response to a provided conversation. To learn how to use the Chat API with Streaming and RAG follow our Text Generation guides.
+     * Generates a message from the model in response to a provided conversation. To learn more about the features of the Chat API follow our [Text Generation guides](https://docs.cohere.com/v2/docs/chat-api).
+     *
+     * Follow the [Migration Guide](https://docs.cohere.com/v2/docs/migrating-v1-to-v2) for instructions on moving from API v1 to API v2.
      *
      * @param {Cohere.V2ChatRequest} request
      * @param {V2.RequestOptions} requestOptions - Request-specific configuration.
@@ -364,7 +368,9 @@ export class V2 {
      *
      * @example
      *     await client.v2.embed({
-     *         model: "model"
+     *         model: "model",
+     *         inputType: Cohere.EmbedInputType.SearchDocument,
+     *         embeddingTypes: [Cohere.EmbeddingType.Float]
      *     })
      */
     public async embed(

diff --git a/src/api/resources/v2/client/requests/V2ChatRequest.ts b/src/api/resources/v2/client/requests/V2ChatRequest.ts
@@ -15,7 +15,7 @@ import * as Cohere from "../../../../index";
  *     }
  */
 export interface V2ChatRequest {
-    /** The name of a compatible [Cohere model](https://docs.cohere.com/docs/models) (such as command-r or command-r-plus) or the ID of a [fine-tuned](https://docs.cohere.com/docs/chat-fine-tuning) model. */
+    /** The name of a compatible [Cohere model](https://docs.cohere.com/v2/docs/models) (such as command-r or command-r-plus) or the ID of a [fine-tuned](https://docs.cohere.com/v2/docs/chat-fine-tuning) model. */
     model: string;
     messages: Cohere.ChatMessages;
     /**
@@ -33,19 +33,19 @@ export interface V2ChatRequest {
     citationOptions?: Cohere.CitationOptions;
     responseFormat?: Cohere.ResponseFormatV2;
     /**
-     * Used to select the [safety instruction](/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
+     * Used to select the [safety instruction](https://docs.cohere.com/v2/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
      * When `OFF` is specified, the safety instruction will be omitted.
      *
      * Safety modes are not yet configurable in combination with `tools`, `tool_results` and `documents` parameters.
      *
-     * **Note**: This parameter is only compatible with models [Command R 08-2024](/docs/command-r#august-2024-release), [Command R+ 08-2024](/docs/command-r-plus#august-2024-release) and newer.
-     *
-     * Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+     * **Note**: This parameter is only compatible with models [Command R 08-2024](https://docs.cohere.com/v2/docs/command-r#august-2024-release), [Command R+ 08-2024](https://docs.cohere.com/v2/docs/command-r-plus#august-2024-release) and newer.
      *
      */
     safetyMode?: Cohere.V2ChatRequestSafetyMode;
     /**
-     * The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
+     * The maximum number of tokens the model will generate as part of the response.
+     *
+     * **Note**: Setting a low value may result in incomplete generations.
      *
      */
     maxTokens?: number;

diff --git a/src/api/resources/v2/client/requests/V2ChatStreamRequest.ts b/src/api/resources/v2/client/requests/V2ChatStreamRequest.ts
@@ -44,7 +44,7 @@ import * as Cohere from "../../../../index";
  *     }
  */
 export interface V2ChatStreamRequest {
-    /** The name of a compatible [Cohere model](https://docs.cohere.com/docs/models) (such as command-r or command-r-plus) or the ID of a [fine-tuned](https://docs.cohere.com/docs/chat-fine-tuning) model. */
+    /** The name of a compatible [Cohere model](https://docs.cohere.com/v2/docs/models) (such as command-r or command-r-plus) or the ID of a [fine-tuned](https://docs.cohere.com/v2/docs/chat-fine-tuning) model. */
     model: string;
     messages: Cohere.ChatMessages;
     /**
@@ -62,19 +62,19 @@ export interface V2ChatStreamRequest {
     citationOptions?: Cohere.CitationOptions;
     responseFormat?: Cohere.ResponseFormatV2;
     /**
-     * Used to select the [safety instruction](/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
+     * Used to select the [safety instruction](https://docs.cohere.com/v2/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
      * When `OFF` is specified, the safety instruction will be omitted.
      *
      * Safety modes are not yet configurable in combination with `tools`, `tool_results` and `documents` parameters.
      *
-     * **Note**: This parameter is only compatible with models [Command R 08-2024](/docs/command-r#august-2024-release), [Command R+ 08-2024](/docs/command-r-plus#august-2024-release) and newer.
-     *
-     * Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+     * **Note**: This parameter is only compatible with models [Command R 08-2024](https://docs.cohere.com/v2/docs/command-r#august-2024-release), [Command R+ 08-2024](https://docs.cohere.com/v2/docs/command-r-plus#august-2024-release) and newer.
      *
      */
     safetyMode?: Cohere.V2ChatStreamRequestSafetyMode;
     /**
-     * The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
+     * The maximum number of tokens the model will generate as part of the response.
+     *
+     * **Note**: Setting a low value may result in incomplete generations.
      *
      */
     maxTokens?: number;

diff --git a/src/api/resources/v2/client/requests/V2EmbedRequest.ts b/src/api/resources/v2/client/requests/V2EmbedRequest.ts
@@ -7,7 +7,9 @@ import * as Cohere from "../../../../index";
 /**
  * @example
  *     {
- *         model: "model"
+ *         model: "model",
+ *         inputType: Cohere.EmbedInputType.SearchDocument,
+ *         embeddingTypes: [Cohere.EmbeddingType.Float]
  *     }
  */
 export interface V2EmbedRequest {
@@ -36,7 +38,7 @@ export interface V2EmbedRequest {
      * * `embed-multilingual-v2.0`  768
      */
     model: string;
-    inputType?: Cohere.EmbedInputType;
+    inputType: Cohere.EmbedInputType;
     /**
      * Specifies the types of embeddings you want to get back. Not required and default is None, which returns the Embed Floats response type. Can be one or more of the following types.
      *
@@ -46,7 +48,7 @@ export interface V2EmbedRequest {
      * * `"binary"`: Use this when you want to get back signed binary embeddings. Valid for only v3 models.
      * * `"ubinary"`: Use this when you want to get back unsigned binary embeddings. Valid for only v3 models.
      */
-    embeddingTypes?: Cohere.EmbeddingType[];
+    embeddingTypes: Cohere.EmbeddingType[];
     /**
      * One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
      *

diff --git a/src/api/resources/v2/types/V2ChatRequestSafetyMode.ts b/src/api/resources/v2/types/V2ChatRequestSafetyMode.ts
@@ -3,14 +3,12 @@
  */
 
 /**
- * Used to select the [safety instruction](/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
+ * Used to select the [safety instruction](https://docs.cohere.com/v2/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
  * When `OFF` is specified, the safety instruction will be omitted.
  *
  * Safety modes are not yet configurable in combination with `tools`, `tool_results` and `documents` parameters.
  *
- * **Note**: This parameter is only compatible with models [Command R 08-2024](/docs/command-r#august-2024-release), [Command R+ 08-2024](/docs/command-r-plus#august-2024-release) and newer.
- *
- * Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+ * **Note**: This parameter is only compatible with models [Command R 08-2024](https://docs.cohere.com/v2/docs/command-r#august-2024-release), [Command R+ 08-2024](https://docs.cohere.com/v2/docs/command-r-plus#august-2024-release) and newer.
  */
 export type V2ChatRequestSafetyMode = "CONTEXTUAL" | "STRICT" | "OFF";
 

diff --git a/src/api/resources/v2/types/V2ChatStreamRequestSafetyMode.ts b/src/api/resources/v2/types/V2ChatStreamRequestSafetyMode.ts
@@ -3,14 +3,12 @@
  */
 
 /**
- * Used to select the [safety instruction](/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
+ * Used to select the [safety instruction](https://docs.cohere.com/v2/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`.
  * When `OFF` is specified, the safety instruction will be omitted.
  *
  * Safety modes are not yet configurable in combination with `tools`, `tool_results` and `documents` parameters.
  *
- * **Note**: This parameter is only compatible with models [Command R 08-2024](/docs/command-r#august-2024-release), [Command R+ 08-2024](/docs/command-r-plus#august-2024-release) and newer.
- *
- * Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+ * **Note**: This parameter is only compatible with models [Command R 08-2024](https://docs.cohere.com/v2/docs/command-r#august-2024-release), [Command R+ 08-2024](https://docs.cohere.com/v2/docs/command-r-plus#august-2024-release) and newer.
  */
 export type V2ChatStreamRequestSafetyMode = "CONTEXTUAL" | "STRICT" | "OFF";
 

diff --git a/src/api/types/AssistantMessage.ts b/src/api/types/AssistantMessage.ts
@@ -9,6 +9,7 @@ import * as Cohere from "../index";
  */
 export interface AssistantMessage {
     toolCalls?: Cohere.ToolCallV2[];
+    /** A chain-of-thought style reflection and plan that the model generates when working with Tools. */
     toolPlan?: string;
     content?: Cohere.AssistantMessageContent;
     citations?: Cohere.Citation[];

diff --git a/src/api/types/AssistantMessageResponse.ts b/src/api/types/AssistantMessageResponse.ts
@@ -10,6 +10,7 @@ import * as Cohere from "../index";
 export interface AssistantMessageResponse {
     role: "assistant";
     toolCalls?: Cohere.ToolCallV2[];
+    /** A chain-of-thought style reflection and plan that the model generates when working with Tools. */
     toolPlan?: string;
     content?: Cohere.AssistantMessageResponseContentItem[];
     citations?: Cohere.Citation[];

diff --git a/src/api/types/ChatFinishReason.ts b/src/api/types/ChatFinishReason.ts
@@ -4,22 +4,19 @@
 
 /**
  * The reason a chat request has finished.
+ *
+ * - **complete**: The model finished sending a complete message.
+ * - **max_tokens**: The number of generated tokens exceeded the model's context length or the value specified via the `max_tokens` parameter.
+ * - **stop_sequence**: One of the provided `stop_sequence` entries was reached in the model's generation.
+ * - **tool_call**: The model generated a Tool Call and is expecting a Tool Message in return
+ * - **error**: The generation failed due to an internal error
  */
-export type ChatFinishReason =
-    | "complete"
-    | "stop_sequence"
-    | "max_tokens"
-    | "tool_call"
-    | "error"
-    | "content_blocked"
-    | "error_limit";
+export type ChatFinishReason = "COMPLETE" | "STOP_SEQUENCE" | "MAX_TOKENS" | "TOOL_CALL" | "ERROR";
 
 export const ChatFinishReason = {
-    Complete: "complete",
-    StopSequence: "stop_sequence",
-    MaxTokens: "max_tokens",
-    ToolCall: "tool_call",
-    Error: "error",
-    ContentBlocked: "content_blocked",
-    ErrorLimit: "error_limit",
+    Complete: "COMPLETE",
+    StopSequence: "STOP_SEQUENCE",
+    MaxTokens: "MAX_TOKENS",
+    ToolCall: "TOOL_CALL",
+    Error: "ERROR",
 } as const;
diff --git a/src/api/types/ChatMessages.ts b/src/api/types/ChatMessages.ts
@@ -7,6 +7,6 @@ import * as Cohere from "../index";
 /**
  * A list of chat messages in chronological order, representing a conversation between the user and the model.
  *
- * Messages can be from `User`, `Assistant`, `Tool` and `System` roles. Learn more about messages and roles in [the Chat API guide](https://docs.cohere.com/docs/chat-api).
+ * Messages can be from `User`, `Assistant`, `Tool` and `System` roles. Learn more about messages and roles in [the Chat API guide](https://docs.cohere.com/v2/docs/chat-api).
  */
 export type ChatMessages = Cohere.ChatMessageV2[];
diff --git a/src/api/types/Citation.ts b/src/api/types/Citation.ts
@@ -8,8 +8,11 @@ import * as Cohere from "../index";
  * Citation information containing sources and the text cited.
  */
 export interface Citation {
+    /** Start index of the cited snippet in the original source text. */
     start?: number;
+    /** End index of the cited snippet in the original source text. */
     end?: number;
+    /** Text snippet that is being cited. */
     text?: string;
     sources?: Cohere.Source[];
 }
diff --git a/src/api/types/JsonResponseFormatV2.ts b/src/api/types/JsonResponseFormatV2.ts
@@ -4,7 +4,7 @@
 
 export interface JsonResponseFormatV2 {
     /**
-     * [BETA] A JSON schema object that the output will adhere to. There are some restrictions we have on the schema, refer to [our guide](/docs/structured-outputs-json#schema-constraints) for more information.
+     * A [JSON schema](https://json-schema.org/overview/what-is-jsonschema) object that the output will adhere to. There are some restrictions we have on the schema, refer to [our guide](/docs/structured-outputs-json#schema-constraints) for more information.
      * Example (required name and age object):
      *
      * ```json

diff --git a/src/api/types/ResponseFormatV2.ts b/src/api/types/ResponseFormatV2.ts
@@ -5,14 +5,17 @@
 import * as Cohere from "../index";
 
 /**
- * Configuration for forcing the model output to adhere to the specified format. Supported on [Command R](https://docs.cohere.com/docs/command-r), [Command R+](https://docs.cohere.com/docs/command-r-plus) and newer models.
+ * Configuration for forcing the model output to adhere to the specified format. Supported on [Command R](https://docs.cohere.com/v2/docs/command-r), [Command R+](https://docs.cohere.com/v2/docs/command-r-plus) and newer models.
  *
- * The model can be forced into outputting JSON objects (with up to 5 levels of nesting) by setting `{ "type": "json_object" }`.
+ * The model can be forced into outputting JSON objects by setting `{ "type": "json_object" }`.
  *
  * A [JSON Schema](https://json-schema.org/) can optionally be provided, to ensure a specific structure.
  *
  * **Note**: When using `{ "type": "json_object" }` your `message` should always explicitly instruct the model to generate a JSON (eg: _"Generate a JSON ..."_) . Otherwise the model may end up getting stuck generating an infinite stream of characters and eventually run out of context length.
- * **Limitation**: The parameter is not supported in RAG mode (when any of `connectors`, `documents`, `tools`, `tool_results` are provided).
+ *
+ * **Note**: When `json_schema` is not specified, the generated object can have up to 5 layers of nesting.
+ *
+ * **Limitation**: The parameter is not supported when used in combinations with the `documents` or `tools` parameters.
  */
 export type ResponseFormatV2 = Cohere.ResponseFormatV2.Text | Cohere.ResponseFormatV2.JsonObject;
 

diff --git a/src/api/types/ToolCallV2.ts b/src/api/types/ToolCallV2.ts
@@ -5,7 +5,7 @@
 import * as Cohere from "../index";
 
 /**
- * A array of tool calls to be made.
+ * An array of tool calls to be made.
  */
 export interface ToolCallV2 {
     id?: string;

diff --git a/src/serialization/resources/v2/client/requests/V2EmbedRequest.ts b/src/serialization/resources/v2/client/requests/V2EmbedRequest.ts
@@ -14,11 +14,8 @@ export const V2EmbedRequest: core.serialization.Schema<serializers.V2EmbedReques
         texts: core.serialization.list(core.serialization.string()).optional(),
         images: core.serialization.list(core.serialization.string()).optional(),
         model: core.serialization.string(),
-        inputType: core.serialization.property("input_type", EmbedInputType.optional()),
-        embeddingTypes: core.serialization.property(
-            "embedding_types",
-            core.serialization.list(EmbeddingType).optional()
-        ),
+        inputType: core.serialization.property("input_type", EmbedInputType),
+        embeddingTypes: core.serialization.property("embedding_types", core.serialization.list(EmbeddingType)),
         truncate: V2EmbedRequestTruncate.optional(),
     });
 
@@ -27,8 +24,8 @@ export declare namespace V2EmbedRequest {
         texts?: string[] | null;
         images?: string[] | null;
         model: string;
-        input_type?: EmbedInputType.Raw | null;
-        embedding_types?: EmbeddingType.Raw[] | null;
+        input_type: EmbedInputType.Raw;
+        embedding_types: EmbeddingType.Raw[];
         truncate?: V2EmbedRequestTruncate.Raw | null;
     }
 }
diff --git a/src/serialization/types/ChatFinishReason.ts b/src/serialization/types/ChatFinishReason.ts
@@ -7,16 +7,8 @@ import * as Cohere from "../../api/index";
 import * as core from "../../core";
 
 export const ChatFinishReason: core.serialization.Schema<serializers.ChatFinishReason.Raw, Cohere.ChatFinishReason> =
-    core.serialization.enum_([
-        "complete",
-        "stop_sequence",
-        "max_tokens",
-        "tool_call",
-        "error",
-        "content_blocked",
-        "error_limit",
-    ]);
+    core.serialization.enum_(["COMPLETE", "STOP_SEQUENCE", "MAX_TOKENS", "TOOL_CALL", "ERROR"]);
 
 export declare namespace ChatFinishReason {
-    type Raw = "complete" | "stop_sequence" | "max_tokens" | "tool_call" | "error" | "content_blocked" | "error_limit";
+    type Raw = "COMPLETE" | "STOP_SEQUENCE" | "MAX_TOKENS" | "TOOL_CALL" | "ERROR";
 }