@visgate_ai/client 0.2.22 → 0.3.4

package/README.md

@@ -1,6 +1,6 @@
 # @visgate_ai/client
 
-JavaScript/TypeScript SDK for the [Visgate API](https://visgateai.com) — one client for image and video generation across Fal, Replicate, and Runway.
+JavaScript/TypeScript SDK for the [Visgate API](https://visgateai.com) — one client for image and video generation across Fal, Replicate, Runway, and RunPod deployments.
 
 Works in Node.js (18+), browsers, and with React, Vite, Next.js, and vanilla JS.
 
@@ -33,7 +33,7 @@ console.log(result.imageUrl);
 
 ## Features
 
-- **One client, three providers.** Fal, Replicate, and Runway behind a single API.
+- **One client, multi-provider.** Fal, Replicate, Runway, and RunPod deployments behind a single API.
 - **Managed and BYOK modes.** Use Visgate-managed keys or bring your own.
 - **Promise-based API.** All methods return Promises; use `async/await` or `.then()`.
 - **Automatic retries.** Transient errors (429, 5xx) are retried with exponential backoff.
@@ -86,6 +86,7 @@ const client = new Client({
   falKey: "fal_...",
   replicateKey: "r8_...",
   runwayKey: "rw_...",
+  runpodKey: "rpa_...",
 });
 ```
 
@@ -205,6 +206,36 @@ const keys = await client.providers.listKeys();
 const balances = await client.providers.balances();
 ```
 
+### Deployments (RunPod BYOK)
+
+```javascript
+// Create deployment from HuggingFace model
+const created = await client.deployments.create({
+  hfModelId: "stabilityai/stable-diffusion-xl-base-1.0",
+  gpuTier: "medium",
+  task: "text2img",
+});
+
+// List deployments and select one
+const list = await client.deployments.list();
+const dep = list.deployments[0];
+
+// Get current status/details
+const detail = await client.deployments.get(dep.deploymentId);
+console.log(detail.status, detail.endpointUrl);
+
+// Run inference on ready deployment
+const run = await client.deployments.run(dep.deploymentId, {
+  prompt: "cinematic cat portrait",
+});
+console.log(run);
+
+// Optional helpers
+const logs = await client.deployments.getLogs(dep.deploymentId);
+const cost = await client.deployments.getCost(dep.deploymentId);
+const gpus = await client.deployments.listGpus();
+```
+
 ### Health Check
 
 ```javascript
@@ -242,6 +273,7 @@ try {
 | `falKey`     | —                           | Fal BYOK key                   |
 | `replicateKey` | —                         | Replicate BYOK key             |
 | `runwayKey`  | —                           | Runway BYOK key                |
+| `runpodKey`  | —                           | RunPod BYOK key (`X-Runpod-Key`) |
 
 ## AsyncClient
 
@@ -256,7 +288,7 @@ const result = await client.generate("a sunset");
 
 ## Repository structure
 
-- **`src/`** — @visgate_ai/client (client library): `generate`, `images`, `videos`, `models`, `requests` (async status), `usage`, `providers`, `billing`
+- **`src/`** — @visgate_ai/client (client library): `generate`, `images`, `videos`, `models`, `requests` (async status), `usage`, `providers`, `deployments`, `billing`
 - **`server-proxy/`** — `@visgate_ai/server-proxy`: server-side proxy for Next.js and other Node runtimes. Install with `npm install @visgate_ai/server-proxy` or use locally from this repo.
 - **`examples/`** — Next.js, vanilla, and Vite examples
 

package/dist/index.cjs

@@ -326,6 +326,219 @@ var Models = class {
   }
 };
 
+// src/resources/deployments.ts
+function deploymentInfoFromResponse(data) {
+  return {
+    deploymentId: data.deployment_id ?? data.deploymentId ?? "",
+    modelId: data.model_id ?? data.modelId,
+    status: data.status ?? "unknown",
+    endpointUrl: data.endpoint_url ?? data.endpointUrl,
+    provider: data.provider ?? "runpod",
+    createdAt: data.created_at ?? data.createdAt,
+    gpuAllocated: data.gpu_allocated ?? data.gpuAllocated,
+    modelVramGb: data.model_vram_gb ?? data.modelVramGb,
+    readyAt: data.ready_at ?? data.readyAt,
+    error: data.error ?? null
+  };
+}
+function deploymentListResponseFromResponse(data) {
+  const deployments = data.deployments ?? [];
+  return { deployments: deployments.map(deploymentInfoFromResponse) };
+}
+function deploymentGpuInfoFromResponse(data) {
+  return {
+    id: data.id ?? "",
+    displayName: data.display_name ?? data.displayName ?? "",
+    memoryGb: data.memory_gb ?? data.memoryGb ?? 0,
+    secureCloud: Boolean(data.secure_cloud ?? data.secureCloud),
+    communityCloud: Boolean(data.community_cloud ?? data.communityCloud),
+    bidPricePerHr: data.bid_price_per_hr ?? data.bidPricePerHr,
+    pricePerHr: data.price_per_hr ?? data.pricePerHr
+  };
+}
+function deploymentGpuListResponseFromResponse(data) {
+  const gpus = data.gpus ?? [];
+  return { gpus: gpus.map(deploymentGpuInfoFromResponse) };
+}
+function deploymentLogsResponseFromResponse(data) {
+  const rawLogs = data.logs ?? [];
+  return {
+    deploymentId: data.deployment_id ?? data.deploymentId ?? "",
+    logs: rawLogs.map((entry) => ({
+      timestamp: entry.timestamp ?? "",
+      level: entry.level ?? "INFO",
+      message: entry.message ?? ""
+    }))
+  };
+}
+function deploymentCostResponseFromResponse(data) {
+  return {
+    deploymentId: data.deployment_id ?? data.deploymentId ?? "",
+    status: data.status ?? "unknown",
+    gpuAllocated: data.gpu_allocated ?? data.gpuAllocated,
+    hoursRunning: data.hours_running ?? data.hoursRunning,
+    pricePerHourUsd: data.price_per_hour_usd ?? data.pricePerHourUsd,
+    estimatedCostUsd: data.estimated_cost_usd ?? data.estimatedCostUsd,
+    note: data.note ?? null
+  };
+}
+var Deployments = class {
+  constructor(_client) {
+    this._client = _client;
+  }
+  async create(options) {
+    const data = await this._client._request("POST", "/deployments", {
+      body: JSON.stringify({
+        model_name: options.modelName,
+        hf_model_id: options.hfModelId,
+        gpu_tier: options.gpuTier,
+        region: options.region,
+        hf_token: options.hfToken,
+        runpod_key: options.runpodKey,
+        webhook_url: options.webhookUrl,
+        cache_scope: options.cacheScope,
+        provider: options.provider,
+        task: options.task,
+        user_s3_url: options.userS3Url,
+        user_aws_access_key_id: options.userAwsAccessKeyId,
+        user_aws_secret_access_key: options.userAwsSecretAccessKey,
+        user_aws_endpoint_url: options.userAwsEndpointUrl
+      })
+    });
+    return deploymentInfoFromResponse(data);
+  }
+  async list() {
+    const data = await this._client._request("GET", "/deployments");
+    return deploymentListResponseFromResponse(data);
+  }
+  async get(deploymentId) {
+    const data = await this._client._request(
+      "GET",
+      `/deployments/${encodeURIComponent(deploymentId)}`
+    );
+    return deploymentInfoFromResponse(data);
+  }
+  async delete(deploymentId) {
+    await this._client._request("DELETE", `/deployments/${encodeURIComponent(deploymentId)}`);
+  }
+  async run(deploymentId, input) {
+    const data = await this._client._request("POST", `/deployments/${encodeURIComponent(deploymentId)}/run`, {
+      body: JSON.stringify({ input })
+    });
+    return data;
+  }
+  async getLogs(deploymentId) {
+    const data = await this._client._request(
+      "GET",
+      `/deployments/${encodeURIComponent(deploymentId)}/logs`
+    );
+    return deploymentLogsResponseFromResponse(data);
+  }
+  async getCost(deploymentId) {
+    const data = await this._client._request(
+      "GET",
+      `/deployments/${encodeURIComponent(deploymentId)}/cost`
+    );
+    return deploymentCostResponseFromResponse(data);
+  }
+  async listGpus() {
+    const data = await this._client._request("GET", "/deployments/gpus");
+    return deploymentGpuListResponseFromResponse(data);
+  }
+  /**
+   * Streams deployment status events (SSE).
+   * Returns an abort function to stop streaming.
+   */
+  streamStatus(deploymentId, onEvent, onError) {
+    const controller = new AbortController();
+    const base = this._client.baseUrl.replace(/\/$/, "");
+    const url = `${base}/deployments/${encodeURIComponent(deploymentId)}/stream`;
+    const headers = {};
+    if (this._client.apiKey) headers.Authorization = `Bearer ${this._client.apiKey}`;
+    void (async () => {
+      try {
+        const response = await fetch(url, {
+          method: "GET",
+          headers,
+          signal: controller.signal
+        });
+        if (!response.ok || !response.body) {
+          throw new Error(`SSE stream failed with status ${response.status}`);
+        }
+        const decoder = new TextDecoder();
+        const reader = response.body.getReader();
+        let buffer = "";
+        while (true) {
+          const { value, done } = await reader.read();
+          if (done) break;
+          buffer += decoder.decode(value, { stream: true });
+          const events = buffer.split("\n\n");
+          buffer = events.pop() ?? "";
+          for (const rawEvent of events) {
+            const dataLine = rawEvent.split("\n").find((line) => line.startsWith("data:"));
+            if (!dataLine) continue;
+            const payload = dataLine.slice(5).trim();
+            if (!payload) continue;
+            try {
+              const parsed = JSON.parse(payload);
+              onEvent({
+                deploymentId: parsed.deployment_id ?? parsed.deploymentId ?? deploymentId,
+                status: parsed.status,
+                endpointUrl: parsed.endpoint_url ?? parsed.endpointUrl,
+                estimatedRemainingSeconds: parsed.estimated_remaining_seconds,
+                error: parsed.error
+              });
+            } catch {
+            }
+          }
+        }
+      } catch (err) {
+        if (!controller.signal.aborted) {
+          const error = err instanceof Error ? err : new Error(String(err));
+          onError?.(error);
+        }
+      }
+    })();
+    return () => controller.abort();
+  }
+};
+
+// src/resources/hf-models.ts
+var HF_API_BASE = "https://huggingface.co/api/models";
+function normalizeModel(raw) {
+  const id = raw.id ?? raw.modelId ?? "";
+  return {
+    id,
+    modelId: raw.modelId ?? id,
+    pipelineTag: raw.pipeline_tag ?? "",
+    libraryName: raw.library_name,
+    likes: raw.likes,
+    downloads: raw.downloads
+  };
+}
+var HfModels = class {
+  async list(options = {}) {
+    const task = options.task ?? "text-to-image";
+    const limit = Math.min(Math.max(options.limit ?? 50, 1), 100);
+    const params = new URLSearchParams();
+    params.set("pipeline_tag", task);
+    params.set("limit", String(limit));
+    if (options.search && options.search.trim()) {
+      params.set("search", options.search.trim());
+    }
+    const url = `${HF_API_BASE}?${params.toString()}`;
+    const response = await fetch(url);
+    if (!response.ok) {
+      throw new Error(`Hugging Face API error: ${response.status} ${response.statusText}`);
+    }
+    const data = await response.json();
+    if (!Array.isArray(data)) {
+      return [];
+    }
+    return data.map((item) => normalizeModel(item));
+  }
+};
+
 // src/resources/providers.ts
 function providerKeyInfoFromResponse(data) {
   return {
@@ -593,7 +806,7 @@ var DEFAULT_BASE_URL = "https://visgateai.com/api/v1";
 var DEFAULT_TIMEOUT = 12e4;
 var DEFAULT_MAX_RETRIES = 2;
 var RETRYABLE_STATUS_CODES = /* @__PURE__ */ new Set([429, 500, 502, 503, 504]);
-var SDK_VERSION = "0.2.2";
+var SDK_VERSION = "0.3.3";
 function getVersion() {
   try {
     if (typeof __VERSION__ !== "undefined") return __VERSION__;
@@ -610,6 +823,7 @@ function buildHeaders(apiKey, options) {
   if (options.falKey) headers["X-Fal-Key"] = options.falKey;
   if (options.replicateKey) headers["X-Replicate-Key"] = options.replicateKey;
   if (options.runwayKey) headers["X-Runway-Key"] = options.runwayKey;
+  if (options.runpodKey) headers["X-Runpod-Key"] = options.runpodKey;
   return headers;
 }
 function backoff(attempt) {
@@ -674,7 +888,8 @@ var Client = class {
     this.headers = buildHeaders(this.apiKey, options.proxyUrl ? {} : {
       falKey: options.falKey,
       replicateKey: options.replicateKey,
-      runwayKey: options.runwayKey
+      runwayKey: options.runwayKey,
+      runpodKey: options.runpodKey
     });
     this.images = new Images(this);
     this.models = new Models(this);
@@ -682,6 +897,8 @@ var Client = class {
     this.requests = new Requests(this);
     this.usage = new Usage(this);
     this.providers = new Providers(this);
+    this.deployments = new Deployments(this);
+    this.hfModels = new HfModels();
     this.billing = new Billing(this);
     this._generate = new Generate(this);
   }
@@ -771,13 +988,15 @@ var AsyncClient = class extends Client {
 };
 
 // src/index.ts
-var VERSION = "0.2.2";
+var VERSION = "0.3.4";
 
 exports.AsyncClient = AsyncClient;
 exports.AuthenticationError = AuthenticationError;
 exports.Billing = Billing;
 exports.Client = Client;
+exports.Deployments = Deployments;
 exports.Generate = Generate;
+exports.HfModels = HfModels;
 exports.Images = Images;
 exports.Models = Models;
 exports.ProviderError = ProviderError;
@@ -793,6 +1012,12 @@ exports.VisgateConnectionError = VisgateConnectionError;
 exports.VisgateError = VisgateError;
 exports.VisgateTimeoutError = VisgateTimeoutError;
 exports.billingInfoFromResponse = billingInfoFromResponse;
+exports.deploymentCostResponseFromResponse = deploymentCostResponseFromResponse;
+exports.deploymentGpuInfoFromResponse = deploymentGpuInfoFromResponse;
+exports.deploymentGpuListResponseFromResponse = deploymentGpuListResponseFromResponse;
+exports.deploymentInfoFromResponse = deploymentInfoFromResponse;
+exports.deploymentListResponseFromResponse = deploymentListResponseFromResponse;
+exports.deploymentLogsResponseFromResponse = deploymentLogsResponseFromResponse;
 exports.featuredSectionFromResponse = featuredSectionFromResponse;
 exports.generateResultFromResponse = generateResultFromResponse;
 exports.imageResultFromResponse = imageResultFromResponse;