notdiamond 1.1.4 → 2.0.0-rc1

package/resources/routing.mjs

@@ -0,0 +1,159 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+import { APIResource } from "../core/resource.mjs";
+import { buildHeaders } from "../internal/headers.mjs";
+import { multipartFormRequestOptions } from "../internal/uploads.mjs";
+export class Routing extends APIResource {
+    /**
+     * Survey Response
+     *
+     * @example
+     * ```ts
+     * const response = await client.routing.createSurveyResponse({
+     *   constraint_priorities: 'constraint_priorities',
+     *   email: 'email',
+     *   llm_providers: 'llm_providers',
+     *   use_case_desc: 'use_case_desc',
+     *   user_id: 'user_id',
+     *   'x-token': 'x-token',
+     * });
+     * ```
+     */
+    createSurveyResponse(params, options) {
+        const { 'x-token': xToken, ...body } = params;
+        return this._client.post('/v2/pzn/surveyResponse', multipartFormRequestOptions({ body, ...options, headers: buildHeaders([{ 'x-token': xToken }, options?.headers]) }, this._client));
+    }
+    /**
+     * Select the optimal LLM to handle your query based on Not Diamond's routing
+     * algorithm.
+     *
+     * This endpoint analyzes your messages and returns the best-suited model from your
+     * specified providers. The router considers factors like query complexity, model
+     * capabilities, cost, and latency based on your preferences.
+     *
+     * **Key Features:**
+     *
+     * - Intelligent routing across multiple LLM providers
+     * - Support for custom routers trained on your evaluation data
+     * - Optional cost/latency optimization
+     * - Function calling support for compatible models
+     * - Privacy-preserving content hashing
+     *
+     * **Usage:**
+     *
+     * 1. Pass your messages in OpenAI format (array of objects with 'role' and
+     *    'content')
+     * 2. Specify which LLM providers you want to route between
+     * 3. Optionally provide a preference_id for personalized routing
+     * 4. Receive a recommended model and session_id
+     * 5. Use the session_id to submit feedback and improve routing
+     *
+     * **Related Endpoints:**
+     *
+     * - `POST /v2/preferences/userPreferenceCreate` - Create a preference ID for
+     *   personalized routing
+     * - `POST /v2/report/metrics/feedback` - Submit feedback on routing decisions
+     * - `POST /v2/pzn/trainCustomRouter` - Train a custom router on your evaluation
+     *   data
+     *
+     * @example
+     * ```ts
+     * const response = await client.routing.selectModel({
+     *   llm_providers: [
+     *     { provider: 'openai', model: 'gpt-4o' },
+     *     {
+     *       provider: 'anthropic',
+     *       model: 'claude-3-5-sonnet-20241022',
+     *     },
+     *     { provider: 'google', model: 'gemini-1.5-pro' },
+     *   ],
+     *   messages: [
+     *     {
+     *       role: 'system',
+     *       content: 'You are a helpful assistant.',
+     *     },
+     *     {
+     *       role: 'user',
+     *       content: 'Explain quantum computing in simple terms',
+     *     },
+     *   ],
+     * });
+     * ```
+     */
+    selectModel(params, options) {
+        const { type, ...body } = params;
+        return this._client.post('/v2/modelRouter/modelSelect', { query: { type }, body, ...options });
+    }
+    /**
+     * Train a custom router on your evaluation data to optimize routing for your
+     * specific use case.
+     *
+     * This endpoint allows you to train a domain-specific router that learns which
+     * models perform best for different types of queries in your application. The
+     * router analyzes your evaluation dataset, clusters similar queries, and learns
+     * model performance patterns.
+     *
+     * **Training Process:**
+     *
+     * 1. Upload a CSV file with your evaluation data
+     * 2. Specify which models to route between
+     * 3. Define the evaluation metric (score column)
+     * 4. The system trains asynchronously and returns a preference_id
+     * 5. Use the preference_id in model_select() calls once training completes
+     *
+     * **Dataset Requirements:**
+     *
+     * - Format: CSV file
+     * - Minimum samples: 25 (more is better for accuracy)
+     * - Required columns:
+     *   - Prompt column (specified in prompt_column parameter)
+     *   - For each model: `{provider}/{model}/score` and `{provider}/{model}/response`
+     *
+     * **Example CSV structure:**
+     *
+     * ```
+     * prompt,openai/gpt-4o/score,openai/gpt-4o/response,anthropic/claude-3-5-sonnet-20241022/score,anthropic/claude-3-5-sonnet-20241022/response
+     * "Explain quantum computing",0.95,"Quantum computing uses...",0.87,"Quantum computers leverage..."
+     * "Write a Python function",0.82,"def my_function()...",0.91,"Here's a Python function..."
+     * ```
+     *
+     * **Model Selection:**
+     *
+     * - Specify standard models: `{"provider": "openai", "model": "gpt-4o"}`
+     * - Or custom models with pricing:
+     *   `{"provider": "custom", "model": "my-model", "is_custom": true, "input_price": 10.0, "output_price": 30.0, "context_length": 8192, "latency": 1.5}`
+     *
+     * **Training Time:**
+     *
+     * - Training is asynchronous and typically takes 5-15 minutes
+     * - Larger datasets or more models take longer
+     * - You'll receive a preference_id immediately
+     * - Check training status by attempting to use the preference_id in model_select()
+     *
+     * **Best Practices:**
+     *
+     * 1. Use diverse, representative examples from your production workload
+     * 2. Include at least 50-100 samples for best results
+     * 3. Ensure consistent evaluation metrics across all models
+     * 4. Use the same models you plan to route between in production
+     *
+     * **Related Documentation:** See
+     * https://docs.notdiamond.ai/docs/adapting-prompts-to-new-models for detailed
+     * guide.
+     *
+     * @example
+     * ```ts
+     * const response = await client.routing.trainCustomRouter({
+     *   dataset_file: fs.createReadStream('path/to/file'),
+     *   language: 'english',
+     *   llm_providers:
+     *     '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-3-5-sonnet-20241022"}]',
+     *   maximize: true,
+     *   prompt_column: 'prompt',
+     * });
+     * ```
+     */
+    trainCustomRouter(body, options) {
+        return this._client.post('/v2/pzn/trainCustomRouter', multipartFormRequestOptions({ body, ...options }, this._client));
+    }
+}
+//# sourceMappingURL=routing.mjs.map

package/resources/routing.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"routing.mjs","sourceRoot":"","sources":["../src/resources/routing.ts"],"names":[],"mappings":"AAAA,sFAAsF;OAE/E,EAAE,WAAW,EAAE;OAGf,EAAE,YAAY,EAAE;OAEhB,EAAE,2BAA2B,EAAE;AAEtC,MAAM,OAAO,OAAQ,SAAQ,WAAW;IACtC;;;;;;;;;;;;;;OAcG;IACH,oBAAoB,CAClB,MAAyC,EACzC,OAAwB;QAExB,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,GAAG,IAAI,EAAE,GAAG,MAAM,CAAC;QAC9C,OAAO,IAAI,CAAC,OAAO,CAAC,IAAI,CACtB,wBAAwB,EACxB,2BAA2B,CACzB,EAAE,IAAI,EAAE,GAAG,OAAO,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC,EAAE,SAAS,EAAE,MAAM,EAAE,EAAE,OAAO,EAAE,OAAO,CAAC,CAAC,EAAE,EACtF,IAAI,CAAC,OAAO,CACb,CACF,CAAC;IACJ,CAAC;IAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;OAwDG;IACH,WAAW,CACT,MAAgC,EAChC,OAAwB;QAExB,MAAM,EAAE,IAAI,EAAE,GAAG,IAAI,EAAE,GAAG,MAAM,CAAC;QACjC,OAAO,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,6BAA6B,EAAE,EAAE,KAAK,EAAE,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,OAAO,EAAE,CAAC,CAAC;IACjG,CAAC;IAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;OAoEG;IACH,iBAAiB,CACf,IAAoC,EACpC,OAAwB;QAExB,OAAO,IAAI,CAAC,OAAO,CAAC,IAAI,CACtB,2BAA2B,EAC3B,2BAA2B,CAAC,EAAE,IAAI,EAAE,GAAG,OAAO,EAAE,EAAE,IAAI,CAAC,OAAO,CAAC,CAChE,CAAC;IACJ,CAAC;CACF"}

package/resources.d.mts

@@ -0,0 +1,2 @@
+export * from "./resources/index.mjs";
+//# sourceMappingURL=resources.d.mts.map

package/resources.d.mts.map

@@ -0,0 +1 @@
+{"version":3,"file":"resources.d.mts","sourceRoot":"","sources":["src/resources.ts"],"names":[],"mappings":""}

package/resources.d.ts

@@ -0,0 +1,2 @@
+export * from "./resources/index.js";
+//# sourceMappingURL=resources.d.ts.map

package/resources.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"resources.d.ts","sourceRoot":"","sources":["src/resources.ts"],"names":[],"mappings":""}

package/resources.js

@@ -0,0 +1,5 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const tslib_1 = require("./internal/tslib.js");
+tslib_1.__exportStar(require("./resources/index.js"), exports);
+//# sourceMappingURL=resources.js.map

package/resources.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"resources.js","sourceRoot":"","sources":["src/resources.ts"],"names":[],"mappings":";;;AAAA,+DAAkC"}

package/resources.mjs

@@ -0,0 +1,2 @@
+export * from "./resources/index.mjs";
+//# sourceMappingURL=resources.mjs.map

package/resources.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"resources.mjs","sourceRoot":"","sources":["src/resources.ts"],"names":[],"mappings":""}

package/src/api-promise.ts

@@ -0,0 +1,2 @@
+/** @deprecated Import from ./core/api-promise instead */
+export * from './core/api-promise';