@nemesis-oss/ollama-sdk 1.16.0 → 1.17.0

package/dist/index.d.cts

@@ -970,8 +970,8 @@ declare class ModelsClient {
      * model-not-found (404), or VRAM-exhaustion failures.
      */
     pin(model: string): Promise<void>;
-    createBlob(digest: string, data: BinaryBody): Promise<void>;
-    checkBlob(digest: string): Promise<boolean>;
+    createBlob(digest: string, data: BinaryBody, request?: RequestCancellationOptions): Promise<void>;
+    checkBlob(digest: string, request?: RequestCancellationOptions): Promise<boolean>;
     /**
      * Computes a blob digest the way Ollama's content-addressed store expects:
      * SHA-256 over the raw bytes, formatted as `sha256:<64 lowercase hex>`.
@@ -992,17 +992,44 @@ declare class ModelsClient {
      */
     createBlobFromData(data: Uint8Array, opts?: {
         readonly digest?: string | undefined;
-        readonly signal?: AbortSignal | undefined;
-    }): Promise<BlobUploadResult>;
+    } & RequestCancellationOptions): Promise<BlobUploadResult>;
+    /**
+     * Streams a blob upload straight from a web `ReadableStream` — the
+     * multi-gigabyte-safe counterpart of {@link createBlobFromData}. The body
+     * is never materialized in memory: the transport hands the stream to
+     * `fetch` directly (setting `duplex: 'half'`, which Node 18+ requires for
+     * stream bodies), so peak heap usage is a transport-level chunk, not the
+     * blob size.
+     *
+     * The digest must be known up front — it *is* the upload URL
+     * (`/api/blobs/<digest>`), the same content-addressed protocol
+     * `curl -T` performs. Hash first when you don't have it: in-memory bytes
+     * via {@link computeBlobDigest}, files via {@link createBlobFromFile}
+     * (which hashes in a streaming pass). The server verifies the streamed
+     * bytes against the digest and rejects mismatches, so a corrupted or
+     * truncated stream fails the upload instead of poisoning the store.
+     */
+    createBlobFromStream(digest: string, stream: ReadableStream<Uint8Array>, request?: RequestCancellationOptions): Promise<BlobUploadResult>;
     /**
      * Reads a local file and uploads it as a blob (Node.js only — dynamic
      * `node:fs` import, so browser bundles never pull it in). The file name
      * (basename) is what `/api/create`'s `files` map expects as the key, so
      * this returns it alongside the digest.
+     *
+     * Streams both passes in fixed-size chunks — peak heap is O(chunk), not
+     * O(file), so multi-gigabyte GGUFs never enter the Node heap:
+     *
+     *  1. **Hash pass** (skipped when `opts.digest` is provided): the file is
+     *     streamed through `node:crypto`'s incremental SHA-256.
+     *  2. **Upload pass**: `node:fs` createReadStream → web ReadableStream →
+     *     `fetch` body with `duplex: 'half'` (see {@link createBlobFromStream}).
+     *
+     * A pre-existing blob (HEAD 200) skips the upload pass entirely, same as
+     * {@link createBlobFromData}.
      */
     createBlobFromFile(path: string, opts?: {
-        readonly signal?: AbortSignal | undefined;
-    }): Promise<BlobUploadResult & {
+        readonly digest?: string | undefined;
+    } & RequestCancellationOptions): Promise<BlobUploadResult & {
         readonly fileName: string;
     }>;
     /**
@@ -2277,8 +2304,8 @@ declare class OllamaClient {
      */
     readonly getContextLength: (request: ContextDiscoveryRequestOptions) => Promise<DiscoveredContextLength>;
     readonly version: () => Promise<VersionResponse>;
-    readonly createBlob: (digest: string, data: BinaryBody) => Promise<void>;
-    readonly checkBlob: (digest: string) => Promise<boolean>;
+    readonly createBlob: (digest: string, data: BinaryBody, request?: RequestCancellationOptions) => Promise<void>;
+    readonly checkBlob: (digest: string, request?: RequestCancellationOptions) => Promise<boolean>;
     /**
      * Immediately unloads `model` from VRAM. Convenience alias for
      * {@link ModelsClient.unload} — see that method for the full

package/dist/index.d.ts

@@ -970,8 +970,8 @@ declare class ModelsClient {
      * model-not-found (404), or VRAM-exhaustion failures.
      */
     pin(model: string): Promise<void>;
-    createBlob(digest: string, data: BinaryBody): Promise<void>;
-    checkBlob(digest: string): Promise<boolean>;
+    createBlob(digest: string, data: BinaryBody, request?: RequestCancellationOptions): Promise<void>;
+    checkBlob(digest: string, request?: RequestCancellationOptions): Promise<boolean>;
     /**
      * Computes a blob digest the way Ollama's content-addressed store expects:
      * SHA-256 over the raw bytes, formatted as `sha256:<64 lowercase hex>`.
@@ -992,17 +992,44 @@ declare class ModelsClient {
      */
     createBlobFromData(data: Uint8Array, opts?: {
         readonly digest?: string | undefined;
-        readonly signal?: AbortSignal | undefined;
-    }): Promise<BlobUploadResult>;
+    } & RequestCancellationOptions): Promise<BlobUploadResult>;
+    /**
+     * Streams a blob upload straight from a web `ReadableStream` — the
+     * multi-gigabyte-safe counterpart of {@link createBlobFromData}. The body
+     * is never materialized in memory: the transport hands the stream to
+     * `fetch` directly (setting `duplex: 'half'`, which Node 18+ requires for
+     * stream bodies), so peak heap usage is a transport-level chunk, not the
+     * blob size.
+     *
+     * The digest must be known up front — it *is* the upload URL
+     * (`/api/blobs/<digest>`), the same content-addressed protocol
+     * `curl -T` performs. Hash first when you don't have it: in-memory bytes
+     * via {@link computeBlobDigest}, files via {@link createBlobFromFile}
+     * (which hashes in a streaming pass). The server verifies the streamed
+     * bytes against the digest and rejects mismatches, so a corrupted or
+     * truncated stream fails the upload instead of poisoning the store.
+     */
+    createBlobFromStream(digest: string, stream: ReadableStream<Uint8Array>, request?: RequestCancellationOptions): Promise<BlobUploadResult>;
     /**
      * Reads a local file and uploads it as a blob (Node.js only — dynamic
      * `node:fs` import, so browser bundles never pull it in). The file name
      * (basename) is what `/api/create`'s `files` map expects as the key, so
      * this returns it alongside the digest.
+     *
+     * Streams both passes in fixed-size chunks — peak heap is O(chunk), not
+     * O(file), so multi-gigabyte GGUFs never enter the Node heap:
+     *
+     *  1. **Hash pass** (skipped when `opts.digest` is provided): the file is
+     *     streamed through `node:crypto`'s incremental SHA-256.
+     *  2. **Upload pass**: `node:fs` createReadStream → web ReadableStream →
+     *     `fetch` body with `duplex: 'half'` (see {@link createBlobFromStream}).
+     *
+     * A pre-existing blob (HEAD 200) skips the upload pass entirely, same as
+     * {@link createBlobFromData}.
      */
     createBlobFromFile(path: string, opts?: {
-        readonly signal?: AbortSignal | undefined;
-    }): Promise<BlobUploadResult & {
+        readonly digest?: string | undefined;
+    } & RequestCancellationOptions): Promise<BlobUploadResult & {
         readonly fileName: string;
     }>;
     /**
@@ -2277,8 +2304,8 @@ declare class OllamaClient {
      */
     readonly getContextLength: (request: ContextDiscoveryRequestOptions) => Promise<DiscoveredContextLength>;
     readonly version: () => Promise<VersionResponse>;
-    readonly createBlob: (digest: string, data: BinaryBody) => Promise<void>;
-    readonly checkBlob: (digest: string) => Promise<boolean>;
+    readonly createBlob: (digest: string, data: BinaryBody, request?: RequestCancellationOptions) => Promise<void>;
+    readonly checkBlob: (digest: string, request?: RequestCancellationOptions) => Promise<boolean>;
     /**
      * Immediately unloads `model` from VRAM. Convenience alias for
      * {@link ModelsClient.unload} — see that method for the full

package/dist/index.js

@@ -1111,6 +1111,18 @@ function createRequestId() {
   requestSequence += 1;
   return `ollama-http-${requestSequence}`;
 }
+function isWebReadableStreamBody(body) {
+  return typeof body === "object" && body !== null && typeof body.getReader === "function";
+}
+function buildFetchInit(req) {
+  return {
+    method: req.method,
+    headers: req.headers,
+    ...req.body !== void 0 ? { body: req.body } : {},
+    ...req.signal !== void 0 ? { signal: req.signal } : {},
+    ...isWebReadableStreamBody(req.body) ? { duplex: "half" } : {}
+  };
+}
 function sameHeaders(actual, expected) {
   const actualEntries = Object.fromEntries(
     Object.entries(actual).map(([key, value]) => [key.toLowerCase(), value])
@@ -1160,13 +1172,7 @@ var HttpClient = class {
       timestamp: startedAt
     });
     const finalHandler = async (req) => {
-      const init = {
-        method: req.method,
-        headers: req.headers,
-        ...req.body !== void 0 ? { body: req.body } : {},
-        ...req.signal !== void 0 ? { signal: req.signal } : {}
-      };
-      const response = await this.fetchImpl(req.url, init);
+      const response = await this.fetchImpl(req.url, buildFetchInit(req));
       rawResponse = response;
       const responseHeaders = response.headers && typeof response.headers.entries === "function" ? Object.fromEntries(response.headers.entries()) : {};
       return {
@@ -1177,12 +1183,7 @@ var HttpClient = class {
     };
     try {
       if (this.middleware.length === 0) {
-        const response2 = await this.fetchImpl(request.url, {
-          method: request.method,
-          headers: request.headers,
-          ...request.body !== void 0 ? { body: request.body } : {},
-          ...request.signal !== void 0 ? { signal: request.signal } : {}
-        });
+        const response2 = await this.fetchImpl(request.url, buildFetchInit(request));
         if (response2.status >= 200 && response2.status < 300) {
           this.onLifecycleEvent?.({
             type: "success",
@@ -2773,7 +2774,7 @@ var ModelsClient = class {
       { model, singleEndpoint: true }
     );
   }
-  async createBlob(digest, data) {
+  async createBlob(digest, data, request) {
     await this.runner(
       (http, signal) => http.request({
         path: `/api/blobs/${encodeURIComponent(digest)}`,
@@ -2781,10 +2782,10 @@ var ModelsClient = class {
         rawBody: data,
         signal
       }),
-      { singleEndpoint: true }
+      { ...request, singleEndpoint: true }
     );
   }
-  async checkBlob(digest) {
+  async checkBlob(digest, request) {
     try {
       await this.runner(
         (http, signal) => http.request({
@@ -2792,7 +2793,7 @@ var ModelsClient = class {
           method: "HEAD",
           signal
         }),
-        { singleEndpoint: true }
+        { ...request, singleEndpoint: true }
       );
       return true;
     } catch (err) {
@@ -2834,9 +2835,32 @@ var ModelsClient = class {
    */
   async createBlobFromData(data, opts) {
     const digest = opts?.digest ?? await this.computeBlobDigest(data);
-    const alreadyExisted = await this.checkBlob(digest);
+    const alreadyExisted = await this.checkBlob(digest, opts);
     if (!alreadyExisted) {
-      await this.createBlob(digest, data);
+      await this.createBlob(digest, data, opts);
+    }
+    return { digest, alreadyExisted };
+  }
+  /**
+   * Streams a blob upload straight from a web `ReadableStream` — the
+   * multi-gigabyte-safe counterpart of {@link createBlobFromData}. The body
+   * is never materialized in memory: the transport hands the stream to
+   * `fetch` directly (setting `duplex: 'half'`, which Node 18+ requires for
+   * stream bodies), so peak heap usage is a transport-level chunk, not the
+   * blob size.
+   *
+   * The digest must be known up front — it *is* the upload URL
+   * (`/api/blobs/<digest>`), the same content-addressed protocol
+   * `curl -T` performs. Hash first when you don't have it: in-memory bytes
+   * via {@link computeBlobDigest}, files via {@link createBlobFromFile}
+   * (which hashes in a streaming pass). The server verifies the streamed
+   * bytes against the digest and rejects mismatches, so a corrupted or
+   * truncated stream fails the upload instead of poisoning the store.
+   */
+  async createBlobFromStream(digest, stream, request) {
+    const alreadyExisted = await this.checkBlob(digest, request);
+    if (!alreadyExisted) {
+      await this.createBlob(digest, stream, request);
     }
     return { digest, alreadyExisted };
   }
@@ -2845,16 +2869,61 @@ var ModelsClient = class {
    * `node:fs` import, so browser bundles never pull it in). The file name
    * (basename) is what `/api/create`'s `files` map expects as the key, so
    * this returns it alongside the digest.
+   *
+   * Streams both passes in fixed-size chunks — peak heap is O(chunk), not
+   * O(file), so multi-gigabyte GGUFs never enter the Node heap:
+   *
+   *  1. **Hash pass** (skipped when `opts.digest` is provided): the file is
+   *     streamed through `node:crypto`'s incremental SHA-256.
+   *  2. **Upload pass**: `node:fs` createReadStream → web ReadableStream →
+   *     `fetch` body with `duplex: 'half'` (see {@link createBlobFromStream}).
+   *
+   * A pre-existing blob (HEAD 200) skips the upload pass entirely, same as
+   * {@link createBlobFromData}.
    */
   async createBlobFromFile(path, opts) {
     const nodeFsModule = "node:fs";
-    const { promises: fs } = await import(nodeFsModule);
-    const data = await fs.readFile(path);
-    const result = await this.createBlobFromData(new Uint8Array(data), {
-      ...opts
-    });
+    const { createReadStream } = await import(nodeFsModule);
+    const nodeCryptoModule = "node:crypto";
+    const { createHash } = await import(nodeCryptoModule);
+    const nodeStreamModule = "node:stream";
+    const { Readable } = await import(nodeStreamModule);
+    const CHUNK_BYTES = 256 * 1024;
+    let digest = opts?.digest;
+    if (digest === void 0) {
+      const hash = createHash("sha256");
+      const hashStream = createReadStream(path, { highWaterMark: CHUNK_BYTES });
+      try {
+        for await (const chunk of hashStream) {
+          if (opts?.signal?.aborted) {
+            throw new OllamaAbortError("createBlobFromFile: aborted while hashing", {});
+          }
+          hash.update(chunk);
+        }
+      } finally {
+        hashStream.destroy();
+      }
+      digest = `sha256:${hash.digest("hex")}`;
+    }
+    const alreadyExisted = await this.checkBlob(digest, opts);
+    if (!alreadyExisted) {
+      const uploadStream = createReadStream(path, { highWaterMark: CHUNK_BYTES });
+      const onAbort = () => {
+        uploadStream.destroy();
+      };
+      opts?.signal?.addEventListener("abort", onAbort, { once: true });
+      try {
+        await this.createBlob(
+          digest,
+          Readable.toWeb(uploadStream),
+          opts
+        );
+      } finally {
+        opts?.signal?.removeEventListener("abort", onAbort);
+      }
+    }
     const fileName = path.split(/[\\/]/).pop() ?? path;
-    return { ...result, fileName };
+    return { digest, alreadyExisted, fileName };
   }
   /**
    * One-shot custom-model publishing from raw GGUF weights, following the
@@ -6194,8 +6263,8 @@ var OllamaClient = class _OllamaClient {
    */
   getContextLength = (request) => this.models.getContextLength(request);
   version = () => this.models.version();
-  createBlob = (digest, data) => this.models.createBlob(digest, data);
-  checkBlob = (digest) => this.models.checkBlob(digest);
+  createBlob = (digest, data, request) => this.models.createBlob(digest, data, request);
+  checkBlob = (digest, request) => this.models.checkBlob(digest, request);
   /**
    * Immediately unloads `model` from VRAM. Convenience alias for
    * {@link ModelsClient.unload} — see that method for the full