sarvam-ai-sdk 0.4.1 → 0.4.2-beta

package/README.md

@@ -1,10 +1,10 @@
-<a href="https://github.com/rajatsandeepsen/sarvam-ai-sdk">
-    <img alt="cover" src="https://github.com/rajatsandeepsen/sarvam-ai-sdk/blob/master/cover.png?raw=true" />
+<a href="https://github.com/sarvamai/sarvam-ai-sdk">
+    <img alt="cover" src="https://github.com/sarvamai/sarvam-ai-sdk/blob/master/cover.png?raw=true" />
 </a>
 
 # AI SDK - Sarvam Provider
 
-The **[Sarvam provider](https://v6.ai-sdk.dev/providers/community-providers/sarvam)** for the [AI SDK](https://v6.ai-sdk.dev/docs)
+The **[Sarvam provider](https://v7.ai-sdk.dev/providers/community-providers/sarvam)** for the [AI SDK](https://v7.ai-sdk.dev/docs)
 contains language model support for the Sarvam chat completion, Text-to-Speech and Speech-to-Text APIs.
 
 ## Setup
@@ -12,19 +12,29 @@ contains language model support for the Sarvam chat completion, Text-to-Speech a
 The **[Sarvam](http://sarvam.ai)** provider is available in the `sarvam-ai-sdk` module. You can install it with
 
 ```bash
-npm i sarvam-ai-sdk ai@6
+npm i sarvam-ai-sdk ai@7
 ```
 
 > [!WARNING]
-> This package only works with Vercel AI-SDK v6, not v7. Make sure to install `ai@6` in your project.
+> This package only works with Vercel AI-SDK v7, not v8. Make sure to install `ai@7` in your project.
+
+### Version Compatibility
+
+| Sarvam AI SDK Version | Vercel AI SDK Version |
+|-----------------------|-----------------------|
+| 0.5.x (beta)			| 8.x.x (beta)			|
+| 0.4.x (current)		| 7.x.x (current)		|
+| 0.3.x 				| 6.x.x 				|
+| 0.2.x					| 5.x.x					|
+| 0.1.x					| 4.x.x					|
 
 ## Provider Instance
 
 You can import the default provider instance `sarvam` from `sarvam-ai-sdk`:
 
-```ts
-import { sarvam } from 'sarvam-ai-sdk';
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+```
 
 Create `.env` file with API key from **[Sarvam Dashboard](https://dashboard.sarvam.ai/)**
 ```bash
@@ -33,182 +43,187 @@ SARVAM_API_KEY="your_api_key"
 
 ## Example
 
-```ts
-import { sarvam } from 'sarvam-ai-sdk';
-import { generateText } from 'ai';
-
-const { text } = await generateText({
-	model: sarvam("sarvam-30b"),
-    prompt: "Translate this to malayalam: 'Keep cooking, guys'",
-});
-
-console.log(text); // പാചകം തുടരൂ, സുഹൃത്തുക്കളേ
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { generateText } from "ai";
+
+const { text } = await generateText({
+	model: sarvam("sarvam-30b", {
+		reasoning_effort: "low",
+	}),
+	prompt: "Translate this to malayalam: 'Keep cooking, guys'",
+});
+
+console.log(text); // പചക തടര, സഹതകള
+```
 
 ## Text-to-Speech
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { experimental_generateSpeech as generateSpeech } from "ai";
-import { writeFile } from "fs/promises";
-
-const { audio } = await generateSpeech({
-    model: sarvam.speech("bulbul:v3", "ml-IN"),
-    text: "പാചകം തുടരൂ, സുഹൃത്തുക്കളേ",
-});
-
-const audioBuffer = Buffer.from(audio.base64, "base64")
-await writeFile("./src/transcript-test.wav", audioBuffer);
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { generateSpeech } from "ai";
+import { writeFile } from "fs/promises";
+
+const { audio } = await generateSpeech({
+	model: sarvam.speech("bulbul:v3", "ml-IN"),
+	text: "പചക തടര, സഹതകള",
+});
+
+const audioBuffer = Buffer.from(audio.base64, "base64");
+await writeFile("./src/transcript-test.wav", audioBuffer);
+```
 
 ## Speech-to-Text
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { experimental_transcribe as transcribe } from "ai";
-import { readFile } from "fs/promises";
-
-const { text } = await transcribe({
-    model: sarvam.transcription("saaras:v3", "en-IN"),
-    audio: await readFile("./src/transcript-test.wav"),
-});
-
-console.log(text); // Pachakam thudaroo, suhruthukkale.
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { transcribe } from "ai";
+import { readFile } from "fs/promises";
+
+const { text } = await transcribe({
+	model: sarvam.transcription("saaras:v3", "en-IN"),
+	audio: await readFile("./src/transcript-test.wav"),
+});
+
+console.log(text); // Pachakam thudaroo, suhruthukkale.
+```
 
 ## Translation
 
 > NB: Only translates `prompt` and `role:user` messages, not `role:system` not `role:assistant`.
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { generateText } from "ai";
-
-const result = await generateText({
-	model: sarvam.translation("mayura:v1", {
-        "from": "ml-IN",
-        "to": "en-IN",
-    }),
-    prompt: "ഇതൊക്കെ ശ്രദ്ധിക്കണ്ടേ അംബാനെ?",
-});
-
-console.log(result.text); // Shouldn't we be careful about this, Ambane?
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { generateText } from "ai";
+
+const result = await generateText({
+	model: sarvam.translation("mayura:v1", {
+		from: "ml-IN",
+		to: "en-IN",
+	}),
+	prompt: "ഇതക ശദകണ അബന?",
+});
+
+console.log(result.text); // Shouldn't we be careful about this, Ambane?
+```
 
 ## Transliterate
 
 > NB: Only transliterates `prompt` and `role:user` messages, not `role:system` not `role:assistant`.
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { generateText } from "ai";
-
-const result = await generateText({
-  model: sarvam.transliterate({
-      to: "ml-IN",
-      from: "en-IN", // optional
-  }),
-  prompt: "eda mone, happy alle?",
-});
-
-console.log(result.text); // എടാ മോനെ, ഹാപ്പി അല്ലേ?
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { generateText } from "ai";
+
+const result = await generateText({
+	model: sarvam.transliterate({
+		to: "ml-IN",
+		from: "en-IN", // optional
+	}),
+	prompt: "eda mone, happy alle?",
+});
+
+console.log(result.text); // എട മന, ഹപ അല?
+```
 
 ## Language Identification
 
 > NB: Only identifies `prompt` and `role:user` messages, not `role:system` not `role:assistant`.
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { generateText } from "ai";
-
-const result = await generateText({
-    model: sarvam.languageIdentification(),
-    prompt: "ബുദ്ധിയാണ് സാറേ ഇവൻ്റെ മെയിൻ",
-});
-
-console.log(result.text); // ml-IN
-```
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+import { generateText } from "ai";
+
+const result = await generateText({
+	model: sarvam.languageIdentification(),
+	prompt: "ബദയണ സറ ഇവൻറ മയൻ",
+});
+
+console.log(result.text); // ml-IN
+```
 
 ## Tool Calling
 
-```ts
-import { z } from "zod";
-import { generateText, tool } from "ai";
-import { sarvam } from "sarvam-ai-sdk";
-
-
-const result = await generateText({
-  model: sarvam("sarvam-30b"),
-  tools: {
-    weather: tool({
-      description: "Get the weather in a location",
-      inputSchema: z.object({
-		location: z.string(),
-      }),
-      execute: async ({ location }) => ({
-        location,
-        temperature: 72 + Math.floor(Math.random() * 21) - 10,
-      }),
-    }),
-  },
-  system: "Your are a helpful AI",
-  prompt: "കൊച്ചിയിലെ കാലാവസ്ഥ എന്താണ്?",
-});
-
-console.log(result.toolResults);
-```
-
-## Generate JSON object
-
-```ts
-import { z } from "zod";
-import { sarvam } from "sarvam-ai-sdk";
-import { generateObject } from 'ai';
-
-const { object } = await generateObject({
-  model: sarvam("sarvam-30b"),
-  schemaName: "Recipe",
-  schemaDescription: "A recipe with a name, ingredients and steps",
-  schema: z.object({
-    recipe: z.object({
-      name: z.string(),
-      ingredients: z.array(z.string()),
-      steps: z.array(z.string()),
-    }),
-  }),
-  prompt: 'Generate a South Indian recipe, in Malayalam',
-});
-
-console.log(object);
-```
+```ts
+import { z } from "zod";
+import { generateText, tool } from "ai";
+import { sarvam } from "sarvam-ai-sdk";
+
+const result = await generateText({
+	model: sarvam("sarvam-30b"),
+	tools: {
+		weather: tool({
+			description: "Get the weather in a location",
+			inputSchema: z.object({
+				location: z.string(),
+			}),
+			execute: async ({ location }) => ({
+				location,
+				temperature: 72 + Math.floor(Math.random() * 21) - 10,
+			}),
+		}),
+	},
+	instructions: "Your are a helpful AI",
+	prompt: "കചയല കലവസ എനണ?",
+});
+
+console.log(result.toolResults);
+```
+
+## Generating Structured Outputs
+
+```ts
+import { z } from "zod";
+import { sarvam } from "sarvam-ai-sdk";
+import { generateText, Output } from "ai";
+
+const { output } = await generateText({
+	model: sarvam("sarvam-105b", {
+		// uncomment to enable direct JSON mode
+		// experimental_json_mode: true,
+	}),
+	output: Output.object({
+		name: "Recipe",
+		description: "A recipe with a name, ingredients and steps",
+		schema: z.object({
+			recipe: z.object({
+				name: z.string(),
+				ingredients: z.array(z.string()),
+				steps: z.array(z.string()),
+			}),
+		}),
+	}),
+	prompt: "Generate a South Indian recipe, in Malayalam",
+});
+
+console.log(output);
+```
 
 ## All APIs
 
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-
-// Text-to-Text + Chat Completion
-sarvam("sarvam-105b");
-sarvam.languageModel("sarvam-30b");
-
-// Text-to-Text + Transliteration
-sarvam.transliterate({ to: "ml-IN", from: "en-IN" });
-
-// Text-to-Text + Translation
-sarvam.translation("mayura:v1", { from: "en-IN", to: "ml-IN" });
-
-// Text-to-Text + Language identification
-sarvam.languageIdentification();
-
-// Text-to-Speech
-sarvam.speech("bulbul:v3", "ml-IN");
-
-// Speech-to-Text
-sarvam.transcription("saaras:v3");
-```
-
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+
+// Text-to-Text + Chat Completion
+sarvam("sarvam-105b");
+sarvam.languageModel("sarvam-30b");
+
+// Text-to-Text + Transliteration
+sarvam.transliterate({ to: "ml-IN", from: "en-IN" });
+
+// Text-to-Text + Translation
+sarvam.translation("mayura:v1", { from: "en-IN", to: "ml-IN" });
+
+// Text-to-Text + Language identification
+sarvam.languageIdentification();
+
+// Text-to-Speech
+sarvam.speech("bulbul:v3", "ml-IN");
+
+// Speech-to-Text
+sarvam.transcription("saaras:v3");
+```
 
 ## Documentation
 
-Please check out the **[Sarvam provider documentation](https://v6.ai-sdk.dev/providers/community-providers/sarvam)** and **[Sarvam API documentation](https://docs.sarvam.ai)** for more information.
+Please check out the **[Sarvam provider documentation](https://v7.ai-sdk.dev/providers/community-providers/sarvam)** and **[Sarvam API documentation](https://docs.sarvam.ai)** for more information.

package/dist/index.d.ts

@@ -1,6 +1,6 @@
 import { FetchFunction } from "@ai-sdk/provider-utils";
-import { LanguageModelV3, SpeechModelV3, TranscriptionModelV3 } from "@ai-sdk/provider";
-import z$1, { z } from "zod";
+import { LanguageModelV4, SpeechModelV4, TranscriptionModelV4 } from "@ai-sdk/provider";
+import { z } from "zod";
 
 //#region src/config.d.ts
 
@@ -64,14 +64,18 @@ interface SarvamProviderSettings {
 //#region src/chat/settings.d.ts
 /**
  * @description Production models
- * @see https://console.sarvam.com/docs/models
+ * @see https://docs.sarvam.ai/api-reference-docs/chat/chat-completions
  */
 type ChatModelId = "sarvam-30b" | "sarvam-105b" | (string & {});
 type ChatSettings = {
   /**
-   * The effort to use for reasoning
+   * The effort to use for reasoning.
+   *
+   * Can be disabled by explicitly setting to "none".
+   *
+   * @default "medium"
    */
-  reasoning_effort?: "low" | "medium" | "high";
+  reasoning_effort?: "none" | "low" | "medium" | "high";
   /**
    * If set to true, the model response will be wiki grounded.
    */
@@ -83,6 +87,18 @@ type ChatSettings = {
    * Keep `n` as `1` to minimize costs.
    */
   n?: number;
+  /**
+   * Enables structured outputs, with or without a specified JSON schema.
+   *
+   * Early & Experimental, Sarvam model might not perform well.
+   *
+   * @example
+   * true: JSON is generated with response_format
+   * false: JSON is generated through tool calling argument
+   *
+   * @default false
+   */
+  experimental_json_mode?: boolean;
 };
 //#endregion
 //#region src/stt/transcription-settings.d.ts
@@ -390,13 +406,14 @@ type TransliterateSettings<S extends boolean = true, T extends SarvamLanguageCod
 type SarvamProvider = {
   /**
    * Creates a model for text generation.
+   *
    * @example
    * 	const { text } = await generateText({
    * 		model: sarvam("sarvam-30b"),
    * 		prompt: "Translate this to malayalam: 'Keep cooking, guys'",
    * 	});
    */
-  (modelId: ChatModelId, settings?: ChatSettings): LanguageModelV3;
+  (modelId: ChatModelId, settings?: ChatSettings): LanguageModelV4;
   /**
    * Creates an Sarvam chat model for text generation.
    *
@@ -406,7 +423,7 @@ type SarvamProvider = {
    * 		prompt: "Translate this to malayalam: 'Keep cooking, guys'",
    * 	});
    */
-  languageModel(modelId: ChatModelId, settings?: ChatSettings): LanguageModelV3;
+  languageModel(modelId: ChatModelId, settings?: ChatSettings): LanguageModelV4;
   /**
    * Creates a Sarvam model for chat.
    *
@@ -416,13 +433,13 @@ type SarvamProvider = {
    * 		prompt: "Translate this to malayalam: 'Keep cooking, guys'",
    * 	});
    */
-  chat(modelId: ChatModelId, settings?: ChatSettings): LanguageModelV3;
+  chat(modelId: ChatModelId, settings?: ChatSettings): LanguageModelV4;
   /**
    * Creates a Sarvam model for transcription.
    *
    * @example
    * 	const { text } = await transcribe({
-   *		model: sarvam.transcription("saaras:v3"),
+   *		model: sarvam.transcription("saaras:v4"),
    *		audio: await readFile("./audio.wav"),
    * 	});
    */
@@ -433,18 +450,18 @@ type SarvamProvider = {
    *
    * @default "unknown"
    */
-  languageCode?: SarvamLanguageCode | MoreSarvamLanguageCode | "unknown", settings?: TranscriptionSettings<T>): TranscriptionModelV3;
+  languageCode?: SarvamLanguageCode | MoreSarvamLanguageCode | "unknown", settings?: TranscriptionSettings<T>): TranscriptionModelV4;
   /**
    * Creates a Sarvam model for speech.
    * @example
    *	const { audio } = await generateSpeech({
-   *		model: sarvam.speech("bulbul:v3", "ml-IN"),
+   *		model: sarvam.speech("bulbul:v4", "ml-IN"),
    *		text: "പാചകം തുടരൂ, സുഹൃത്തുക്കളേ",
    * 	});
    *
    * 	await writeFile("./audio.wav", Buffer.from(audio.base64, "base64"));
    */
-  speech<T extends SpeechModelId>(modelId: T, languageCode: SarvamLanguageCode, settings?: SpeechSettings<T>): SpeechModelV3;
+  speech<T extends SpeechModelId>(modelId: T, languageCode: SarvamLanguageCode, settings?: SpeechSettings<T>): SpeechModelV4;
   /**
    * Creates an Sarvam model for transliterate.
    *
@@ -457,7 +474,7 @@ type SarvamProvider = {
    *		prompt: "eda mone, happy alle?",
    *	});
    */
-  transliterate<T extends SarvamLanguageCode>(settings: TransliterateSettings<false, T>): LanguageModelV3;
+  transliterate<T extends SarvamLanguageCode>(settings: TransliterateSettings<false, T>): LanguageModelV4;
   /**
    * Creates an Sarvam model for translation.
    *
@@ -470,7 +487,7 @@ type SarvamProvider = {
    *		prompt: "ഇതൊക്കെ ശ്രദ്ധിക്കണ്ടേ അംബാനെ?",
    *	});
    */
-  translation<T extends TranslationModelId>(model: T, settings: TranslationSettings<T>): LanguageModelV3;
+  translation<T extends TranslationModelId>(model: T, settings: TranslationSettings<T>): LanguageModelV4;
   /**
    * Creates an Sarvam model for language identification.
    *
@@ -480,7 +497,7 @@ type SarvamProvider = {
    *		prompt: "ബുദ്ധിയാണ് സാറേ ഇവൻ്റെ മെയിൻ",
    *	});
    */
-  languageIdentification(): LanguageModelV3;
+  languageIdentification(): LanguageModelV4;
 };
 //#endregion
 //#region src/provider.d.ts