pareta 0.2.1 → 1.1.0

package/README.md

@@ -69,22 +69,11 @@ const res = await client.chat.completions.create({ model: "auto", messages: [...
 ```
 
 This SDK's unique value is everything AROUND that call — evals on your data,
-auto metrics, the benchmark catalog, and the dedicated-endpoint control plane.
+auto metrics, and the benchmark catalog.
 
-## Dedicated endpoints (when you want to pin one model)
-
-`"auto"` routes per request. When a workload wants one specific open model on
-dedicated capacity, deploy it and call it by endpoint id:
-
-```ts
-const ep = await pa.endpoints.deploy({ task: "invoice-extraction", model: "recommended", wait: true });
-const res = await pa.chat.completions.create({ model: ep.id, messages: [...] });
-
-for (const m of await pa.models.list()) console.log(m.id);
-```
-
-Discovery (`pa.tasks.match`, `pa.tasks.leaderboard`) tells you which open
-models are benchmark-proven for your task and what the frontier baseline costs.
+Discovery (`pa.tasks.match`) tells you whether Pareta has a benchmark-proven
+specialist lane for your workload — describe the task in free text and get
+ranked matching tasks back.
 
 ## Auth
 

package/dist/index.cjs

@@ -174,7 +174,7 @@ function parseSSE(reader, opts) {
 }
 
 // src/version.ts
-var VERSION = "0.1.0";
+var VERSION = "1.1.0";
 
 // src/money.ts
 var MICRO_PER_CENT = 10000n;
@@ -280,47 +280,6 @@ var ModelList = class extends BaseModel {
     return this.data[Symbol.iterator]();
   }
 };
-var Endpoint = class extends BaseModel {
-  get id() {
-    return this.raw.id ?? this.raw.name ?? null;
-  }
-  get name() {
-    return this.raw.name ?? null;
-  }
-  get model() {
-    return this.raw.model ?? null;
-  }
-  get status() {
-    return this.raw.status ?? null;
-  }
-  // Live list sends camelCase `taskName`; the detail record sends `task`.
-  get task() {
-    return this.raw.taskName ?? this.raw.task ?? null;
-  }
-  get url() {
-    return this.raw.url ?? null;
-  }
-  get isLive() {
-    return this.raw.status === "live";
-  }
-  /** Structured-extraction endpoints (contract / SEC / ICD …): the system prompt
-   *  the benchmark used. The proxy applies it automatically when you send no
-   *  `system` message (so quality matches the leaderboard by default); returned
-   *  here so you can read it, or override it with your own `system` message.
-   *  `null` when the task has no injectable prompt (see `promptScaffold`). */
-  get recommendedSystemPrompt() {
-    return this.raw.recommendedSystemPrompt ?? null;
-  }
-  /** Fixed-label classification endpoints: a copy-and-customize `system` prompt
-   *  template. NEVER auto-applied — the categories are yours, not the benchmark's
-   *  — so fill them in and send it as your `system` message. `null` otherwise. */
-  get promptScaffold() {
-    return this.raw.promptScaffold ?? null;
-  }
-};
-function endpointList(raw) {
-  return (raw ?? []).map((e) => new Endpoint(e));
-}
 var Task = class extends BaseModel {
   get id() {
     return this.raw.id ?? null;
@@ -434,47 +393,6 @@ var EvalResult = class extends BaseModel {
     return (this.raw.per_item ?? []).map((it) => new EvalItemResult(it));
   }
 };
-var LeaderboardEntry = class extends BaseModel {
-  get name() {
-    return this.raw.name ?? null;
-  }
-  get kind() {
-    return this.raw.kind ?? null;
-  }
-  get quality() {
-    return this.raw.quality ?? null;
-  }
-  // Raw integer — sub-cent unit rate, NOT floored (see money.ts).
-  get costPerRequestMicroUsd() {
-    return this.raw.cost_per_request_micro_usd ?? null;
-  }
-  get contextK() {
-    return this.raw.context_k ?? null;
-  }
-  get runMode() {
-    return this.raw.run_mode ?? null;
-  }
-};
-var Leaderboard = class extends BaseModel {
-  get taskId() {
-    return this.raw.task_id ?? null;
-  }
-  get metric() {
-    return this.raw.metric ?? null;
-  }
-  get costUnit() {
-    return this.raw.cost_unit ?? null;
-  }
-  get recommended() {
-    return this.raw.recommended ?? null;
-  }
-  get models() {
-    return (this.raw.models ?? []).map((m) => new LeaderboardEntry(m));
-  }
-  get frontier() {
-    return this.raw.frontier ? new LeaderboardEntry(this.raw.frontier) : null;
-  }
-};
 var FrontierModel = class extends BaseModel {
   get id() {
     return this.raw.id ?? null;
@@ -485,14 +403,11 @@ var FrontierModel = class extends BaseModel {
   get vision() {
     return Boolean(this.raw.vision);
   }
-  /** Only meaningful when a task was given: it's on that task's leaderboard. */
+  /** Only meaningful when a task was given: it has benchmark results on that task. */
   get benchmarked() {
     return Boolean(this.raw.benchmarked);
   }
 };
-function leaderboardFrom(raw) {
-  return new Leaderboard(raw ?? {});
-}
 function frontierModels(raw) {
   return (raw?.frontier_models ?? []).map((m) => new FrontierModel(m));
 }
@@ -530,12 +445,53 @@ var EvalRun = class extends BaseModel {
     return (this.raw.results ?? []).map((r) => new EvalResult(r));
   }
 };
+var RerankResult = class extends BaseModel {
+  /** Position of this document in YOUR request's documents array. */
+  get index() {
+    return Number(this.raw.index ?? -1);
+  }
+  /** Calibrated P(relevant) in (0, 1) — thresholdable, not just ordinal. */
+  get relevanceScore() {
+    return Number(this.raw.relevance_score ?? 0);
+  }
+};
+var Rerank = class extends BaseModel {
+  get results() {
+    return (this.raw.results ?? []).map((r) => new RerankResult(r));
+  }
+  get model() {
+    return this.raw.model ?? null;
+  }
+  get pairs() {
+    return this.raw.pairs ?? null;
+  }
+  /** Map the ranked indices back onto the documents you sent — best first. */
+  topDocuments(documents) {
+    return this.results.filter((r) => r.index >= 0 && r.index < documents.length).map((r) => documents[r.index]);
+  }
+};
+var Embeddings = class extends BaseModel {
+  get vectors() {
+    const rows = [...this.raw.data ?? []];
+    rows.sort((a, b) => Number(a.index ?? 0) - Number(b.index ?? 0));
+    return rows.map((r) => r.embedding ?? []);
+  }
+  get model() {
+    return this.raw.model ?? null;
+  }
+  get promptTokens() {
+    return this.raw.usage?.prompt_tokens ?? null;
+  }
+  get length() {
+    return (this.raw.data ?? []).length;
+  }
+};
 
 // src/resources/chat.ts
 var PATH = "/v1/chat/completions";
 function buildBody(params) {
   const { model, messages, stream, ...extra } = params;
-  if (!model) throw new ParetaError("model is required (an endpoint id from endpoints.deploy)");
+  if (!model) throw new ParetaError('model is required (use "auto")');
   if (!messages || messages.length === 0) {
     throw new ParetaError("messages is required and must be non-empty");
   }
@@ -583,99 +539,19 @@ var Models = class {
   }
 };
 
-// src/resources/endpoints.ts
-var BASE = "/v1/endpoints";
-function buildDeployBody(params) {
-  const { task, model, name, wait: _wait, ...extra } = params;
-  if (!task) throw new ParetaError("task is required");
-  const body = { task, model: model || "recommended", ...extra };
-  if (name !== void 0) body.name = name;
-  return body;
-}
-function endpointFromComplete(data) {
-  const ep = data && typeof data === "object" ? data.endpoint : null;
-  return new Endpoint(ep ?? {});
-}
-function deployError(data) {
-  const msg = data && typeof data === "object" ? data.message : String(data);
-  return new ParetaError(`deploy failed: ${msg || "unknown error"}`);
-}
-var EndpointMetrics = class {
-  constructor(client, id) {
-    this.client = client;
-    this.id = id;
-  }
-  client;
-  id;
-  performance(params) {
-    return this.client.request("GET", `${BASE}/${this.id}/performance`, { params });
-  }
-  uptime(params) {
-    return this.client.request("GET", `${BASE}/${this.id}/uptime`, { params });
-  }
-  cost(params) {
-    return this.client.request("GET", `${BASE}/${this.id}/cost`, { params });
-  }
-  quality(params) {
-    return this.client.request("GET", `${BASE}/${this.id}/quality`, { params });
-  }
-  activity(params) {
-    return this.client.request("GET", `${BASE}/${this.id}/activity`, { params });
-  }
-};
-var Endpoints = class {
-  constructor(client) {
-    this.client = client;
-  }
-  client;
-  deploy(params) {
-    const body = buildDeployBody(params);
-    const stream = this.client.stream("POST", BASE, { body, events: true });
-    if (!params.wait) return stream;
-    return this.waitForDeploy(stream);
-  }
-  async waitForDeploy(stream) {
-    for await (const ev of stream) {
-      if (ev.event === "complete") return endpointFromComplete(ev.data);
-      if (ev.event === "error") throw deployError(ev.data);
-    }
-    throw new ParetaError("deploy stream ended without a 'complete' event");
-  }
-  list() {
-    return this.client.request("GET", BASE, { cast: endpointList });
-  }
-  retrieve(endpointId) {
-    return this.client.request("GET", `${BASE}/${endpointId}`, {
-      cast: (raw) => new Endpoint(raw)
-    });
-  }
-  start(endpointId) {
-    return this.client.request("POST", `${BASE}/${endpointId}/start`);
-  }
-  stop(endpointId) {
-    return this.client.request("POST", `${BASE}/${endpointId}/stop`);
-  }
-  async delete(endpointId) {
-    await this.client.request("DELETE", `${BASE}/${endpointId}`);
-  }
-  metrics(endpointId) {
-    return new EndpointMetrics(this.client, endpointId);
-  }
-};
-
 // src/resources/tasks.ts
-var BASE2 = "/v1/tasks";
+var BASE = "/v1/tasks";
 var Tasks = class {
   constructor(client) {
     this.client = client;
   }
   client;
   list() {
-    return this.client.request("GET", BASE2, { cast: taskList });
+    return this.client.request("GET", BASE, { cast: taskList });
   }
   retrieve(taskId, opts = {}) {
     const params = opts.examplesN !== void 0 ? { examples_n: opts.examplesN } : void 0;
-    return this.client.request("GET", `${BASE2}/${taskId}`, {
+    return this.client.request("GET", `${BASE}/${taskId}`, {
       params,
       cast: (raw) => new Task(raw)
     });
@@ -683,25 +559,15 @@ var Tasks = class {
   /** Free-text intent → ranked candidate tasks (the Step-0 backend matcher). */
   match(query, opts = {}) {
     if (!query || !query.trim()) throw new ParetaError("query is required");
-    return this.client.request("POST", `${BASE2}/match`, {
+    return this.client.request("POST", `${BASE}/match`, {
       body: { query, top_k: opts.topK ?? 5 },
       cast: (raw) => new TaskMatch(raw)
     });
   }
-  /** Models ranked by quality/cost for a task (+ recommended + frontier baseline). */
-  leaderboard(taskId) {
-    return this.client.request("GET", `${BASE2}/${taskId}/leaderboard`, {
-      cast: leaderboardFrom
-    });
-  }
-  /** The task's recommended deployable model — what deploy(model:"recommended") resolves to. */
-  async recommended(taskId) {
-    return (await this.leaderboard(taskId)).recommended;
-  }
 };
 
 // src/resources/evals.ts
-var BASE3 = "/v1/eval-sets";
+var BASE2 = "/v1/eval-sets";
 var RUNS = "/v1/eval-runs";
 var FRONTIER = "/v1/eval/frontier-models";
 var INLINE_MAX = 5 * 1024 * 1024;
@@ -775,17 +641,17 @@ var EvalSets = class {
   client;
   create(params) {
     const { files, data } = itemsJsonl(params.task, params.items, params.name);
-    return this.client.request("POST", BASE3, { files, data, cast: evalSetFromCreate });
+    return this.client.request("POST", BASE2, { files, data, cast: evalSetFromCreate });
   }
   list() {
-    return this.client.request("GET", BASE3, { cast: evalSetList });
+    return this.client.request("GET", BASE2, { cast: evalSetList });
   }
   async retrieve(evalSetId) {
-    const raw = await this.client.request("GET", `${BASE3}/${evalSetId}`);
+    const raw = await this.client.request("GET", `${BASE2}/${evalSetId}`);
     return new EvalSet((raw ?? {}).eval_set ?? {});
   }
   async delete(evalSetId) {
-    await this.client.request("DELETE", `${BASE3}/${evalSetId}`);
+    await this.client.request("DELETE", `${BASE2}/${evalSetId}`);
   }
   /**
    * Attach a binary doc (PDF/image) to one row's blob field. Collapses the
@@ -795,14 +661,14 @@ var EvalSets = class {
   async uploadDocument(evalSetId, file, opts) {
     const { blob, filename, size, mime } = await toBlob(file, opts.mime);
     if (size < INLINE_MAX) {
-      return this.client.request("POST", `${BASE3}/${evalSetId}/attach-blob`, {
+      return this.client.request("POST", `${BASE2}/${evalSetId}/attach-blob`, {
         files: { file: { filename, content: blob, contentType: mime } },
         data: { idx: String(opts.idx), field_name: opts.fieldName, mime }
       });
     }
     const minted = await this.client.request(
       "POST",
-      `${BASE3}/${evalSetId}/blob-upload-url`,
+      `${BASE2}/${evalSetId}/blob-upload-url`,
       { body: { idx: opts.idx, field_name: opts.fieldName, mime, file_size: size } }
     );
     const put = await globalThis.fetch(minted.upload_url, {
@@ -814,7 +680,7 @@ var EvalSets = class {
     if (put.status !== 200 && put.status !== 201) {
       throw new ParetaError(`blob upload PUT failed: ${put.status}`);
     }
-    return this.client.request("POST", `${BASE3}/${evalSetId}/blob-upload-complete`, {
+    return this.client.request("POST", `${BASE2}/${evalSetId}/blob-upload-complete`, {
       body: { idx: opts.idx, field_name: opts.fieldName, storage_uri: minted.storage_uri, mime }
     });
   }
@@ -922,9 +788,49 @@ var Auto = class {
   }
 };
 
+// src/resources/retrieval.ts
+function makeRerank(client) {
+  return (query, documents, opts = {}) => {
+    if (!query || !query.trim()) throw new ParetaError("query is required");
+    if (!Array.isArray(documents) || documents.length === 0) {
+      throw new ParetaError("documents must be a non-empty array of strings");
+    }
+    const body = { query, documents };
+    if (opts.topN !== void 0) body.top_n = opts.topN;
+    return client.request("POST", "/v1/rerank", {
+      body,
+      cast: (raw) => new Rerank(raw)
+    });
+  };
+}
+function makeEmbeddings(client) {
+  return (input, opts = {}) => {
+    const texts = typeof input === "string" ? [input] : input;
+    if (!Array.isArray(texts) || texts.length === 0 || texts.some((t) => typeof t !== "string" || !t.trim())) {
+      throw new ParetaError("input must be a non-empty string or array of non-empty strings");
+    }
+    if (opts.inputType !== void 0 && opts.inputType !== "query" && opts.inputType !== "document") {
+      throw new ParetaError('inputType must be "query" or "document"');
+    }
+    const body = { input: texts };
+    if (opts.inputType !== void 0) body.input_type = opts.inputType;
+    return client.request("POST", "/v1/embeddings", {
+      body,
+      cast: (raw) => new Embeddings(raw)
+    });
+  };
+}
+
 // src/client.ts
 var DEFAULT_BASE_URL = "https://api.pareta.ai";
-var DEFAULT_TIMEOUT_MS = 6e4;
+function randomKey() {
+  try {
+    return globalThis.crypto?.randomUUID?.().replace(/-/g, "") ?? Math.random().toString(36).slice(2) + Date.now().toString(36);
+  } catch {
+    return Math.random().toString(36).slice(2) + Date.now().toString(36);
+  }
+}
+var DEFAULT_TIMEOUT_MS = 6e5;
 var DEFAULT_MAX_RETRIES = 2;
 var RETRY_STATUSES = /* @__PURE__ */ new Set([408, 409, 429, 500, 502, 503, 504]);
 function normalizeBaseURL(url) {
@@ -939,10 +845,13 @@ var Pareta = class _Pareta {
   // Resource namespaces (assigned in the constructor; filled in slice by slice).
   chat;
   models;
-  endpoints;
   tasks;
   evals;
   auto;
+  /** Document reranking (the Retrieval precision lane) — `pa.rerank(query, docs, {topN})`. */
+  rerank;
+  /** Text embeddings (the Retrieval recall lane) — `pa.embeddings(input, {inputType})`. */
+  embeddings;
   constructor(options = {}) {
     if (!options.apiKey) {
       throw new ParetaError(
@@ -960,10 +869,11 @@ var Pareta = class _Pareta {
     this.fetchImpl = options.fetch ? f : f.bind(globalThis);
     this.chat = new Chat(this);
     this.models = new Models(this);
-    this.endpoints = new Endpoints(this);
     this.tasks = new Tasks(this);
     this.evals = new Evals(this);
     this.auto = new Auto(this);
+    this.rerank = makeRerank(this);
+    this.embeddings = makeEmbeddings(this);
   }
   /** Build from PARETA_API_KEY (+ optional PARETA_BASE_URL); explicit opts win. */
   static fromEnv(options = {}) {
@@ -1050,6 +960,9 @@ var Pareta = class _Pareta {
     const url = this.buildURL(path, params);
     const isMultipart = files != null || data != null;
     const headers = this.headers({ jsonBody: body != null && !isMultipart });
+    if (method.toUpperCase() === "POST" && !headers["Idempotency-Key"]) {
+      headers["Idempotency-Key"] = `pareta-js-${randomKey()}`;
+    }
     let payload;
     if (isMultipart) {
       payload = this.buildFormData(files, data);
@@ -1091,12 +1004,15 @@ var Pareta = class _Pareta {
   /**
    * Yield parsed SSE objects. Retries ONLY the initial connect/handshake — once
    * bytes are flowing a mid-stream drop raises (re-issuing would re-run a
-   * metered generation / re-trigger a deploy). `events:true` → `{event,data}`.
+   * metered generation). `events:true` → `{event,data}`.
    */
   async *stream(method, path, opts = {}) {
     const { body, params, cast, events } = opts;
     const url = this.buildURL(path, params);
     const headers = this.headers({ stream: true, jsonBody: body != null });
+    if (method.toUpperCase() === "POST" && !headers["Idempotency-Key"]) {
+      headers["Idempotency-Key"] = `pareta-js-${randomKey()}`;
+    }
     const payload = body != null ? JSON.stringify(body) : void 0;
     for (let attempt = 0; attempt <= this.maxRetries; attempt++) {
       let started = false;
@@ -1148,8 +1064,7 @@ exports.ChatCompletion = ChatCompletion;
 exports.ChatCompletionChunk = ChatCompletionChunk;
 exports.Choice = Choice;
 exports.ConflictError = ConflictError;
-exports.Endpoint = Endpoint;
-exports.EndpointMetrics = EndpointMetrics;
+exports.Embeddings = Embeddings;
 exports.EndpointNotReadyError = EndpointNotReadyError;
 exports.EvalItemResult = EvalItemResult;
 exports.EvalResult = EvalResult;
@@ -1159,8 +1074,6 @@ exports.EvalSet = EvalSet;
 exports.EvalSets = EvalSets;
 exports.FrontierModel = FrontierModel;
 exports.InsufficientCreditsError = InsufficientCreditsError;
-exports.Leaderboard = Leaderboard;
-exports.LeaderboardEntry = LeaderboardEntry;
 exports.Message = Message;
 exports.Model = Model;
 exports.ModelList = ModelList;
@@ -1169,6 +1082,8 @@ exports.Pareta = Pareta;
 exports.ParetaError = ParetaError;
 exports.PermissionDeniedError = PermissionDeniedError;
 exports.RateLimitError = RateLimitError;
+exports.Rerank = Rerank;
+exports.RerankResult = RerankResult;
 exports.Task = Task;
 exports.TaskMatch = TaskMatch;
 exports.TaskMatchCandidate = TaskMatchCandidate;