@eltjs/embedding 0.0.0-stage → 0.1.1

package/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 ezzabuzaid
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -1,3 +1,76 @@
-# Temporary Holding Version
+# Embedding
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+`Embedding` is a rule of a computed dataset. It gives each loaded row a vector of its text, made by an AI SDK embedding model, so that a vector search can find rows by meaning.
+
+```ts
+import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
+
+import { ComputedDataset } from '@eltjs/elt-sqlite';
+import { Embedding } from '@eltjs/embedding';
+
+const model = createOpenAICompatible({
+  name: 'llama.cpp',
+  baseURL: 'http://127.0.0.1:8080/v1',
+}).embeddingModel('embeddinggemma-2');
+
+new ComputedDataset({
+  into: destination,
+  name: 'listing_vectors',
+  description: 'The vector of each listing.',
+  from: [listings],
+  compute: new Embedding({
+    model,
+    key: 'id',
+    fields: ['title', 'description'],
+  }),
+});
+```
+
+- `key` is the column that identifies a row. It is the key of the output row.
+- `fields` are the columns whose text makes the vector. The rule joins their text with line breaks. A row with no text in these columns has no vector.
+- The output column `vector` holds a unit vector of float32 values in the byte order of the platform. This is the form that `VectorSearch` of `@zukhruf/embeddings` reads, so the cosine similarity of two vectors is their dot product.
+- The identity of each row is the provider and the id of the model. When you change the model, the next refresh makes every vector again.
+- The rule sends 64 rows to `embedMany` at a time. When the model refuses a call, each row of that call is stored as `failed` with the error, and the next refresh asks again. The load does not fail.
+- To search, declare a view that gives `id` and `vector`, and give its name to `VectorSearch`. A search by publish date, such as `nearest`, also needs `published_at`. A query without a date range does not.
+
+## Give the model its prompts
+
+Some models want a prompt before each text, and a different prompt for a document and for a search text. EmbeddingGemma wants `title: none | text: …` before a document and `task: search result | query: …` before a search text. The rule does not know the model, so it adds no prompt. Wrap the model with `wrapEmbeddingModel` of the AI SDK, one time for documents and one time for search texts:
+
+```ts
+import { embed, wrapEmbeddingModel } from 'ai';
+
+const gemma = local.embeddingModel('embeddinggemma-2');
+const prompted = (modelId: string, prompt: string) =>
+  wrapEmbeddingModel({
+    model: gemma,
+    modelId,
+    middleware: {
+      transformParams: async ({ params }) => ({
+        ...params,
+        values: params.values.map((text) => `${prompt}${text}`),
+      }),
+    },
+  });
+
+const documents = prompted('embeddinggemma-2/document', 'title: none | text: ');
+const searches = prompted(
+  'embeddinggemma-2/query',
+  'task: search result | query: ',
+);
+
+new Embedding({
+  model: documents,
+  key: 'id',
+  fields: ['title', 'description'],
+});
+
+const { embedding } = await embed({ model: searches, value: 'family sedan' });
+new VectorSearch({ database, table: 'listing_vectors' }).query(embedding);
+```
+
+Give each wrapped model its own `modelId`. The identity of a row is the provider and the id of the model, so a new prompt with a new `modelId` makes every vector again.
+
+On 2026-10-27, 42 OpenSooq listings that `source-opensooq-web` crawled got their vectors from EmbeddingGemma 2 in one run. `nearest` of a bicycle listing gave other bicycle listings first. A second run made no vector again.
+
+The package does not start a model or a server. Give it a model that is ready. See [when the pipeline refreshes](../elt/README.md#when-the-pipeline-refreshes) for how a pipeline refreshes the rows.

package/dist/embedding.d.ts

@@ -0,0 +1,28 @@
+import { type EmbeddingModel } from 'ai';
+import { type LoadedRow, Rule, type RuleResult } from '@eltjs/elt';
+export declare class Embedding extends Rule<string, Uint8Array> {
+    #private;
+    readonly key: {
+        readonly name: string;
+        readonly description: string;
+    };
+    readonly output: {
+        readonly vector: {
+            readonly type: 'blob';
+            readonly description: 'The unit vector of the row text, float32 values in the byte order of the platform. NULL unless status is computed.';
+        };
+    };
+    readonly batch = 64;
+    readonly concurrency = 1;
+    constructor({ model, key, fields, }: {
+        model: EmbeddingModel;
+        key: string;
+        fields: readonly string[];
+    });
+    read(row: LoadedRow): {
+        readonly key: string;
+        readonly input: string;
+    } | null;
+    identity(): Promise<string>;
+    compute(texts: readonly string[], signal?: AbortSignal): Promise<readonly RuleResult<Readonly<Record<string, Uint8Array>>>[]>;
+}

package/dist/embedding.js

@@ -0,0 +1,77 @@
+import { embedMany } from 'ai';
+import { Rule, errorMessage, } from '@eltjs/elt';
+// The vector of each loaded row's text, made by an embedding model, so a
+// vector search finds rows by meaning, as pgai's vectorizer and LanceDB's
+// embedding functions keep one beside each row. A vector is stored as a unit
+// vector of float32 values in the platform's byte order, the form
+// @zukhruf/embeddings' VectorSearch reads (its ADR 0005): cosine similarity
+// is then a dot product.
+export class Embedding extends Rule {
+    key;
+    output = {
+        vector: {
+            type: 'blob',
+            description: 'The unit vector of the row text, float32 values in the byte order of the platform. NULL unless status is computed.',
+        },
+    };
+    // Rows embedded and committed together; the model's own limit on values in
+    // one call splits a batch further inside embedMany.
+    batch = 64;
+    // One call at a time: a local model server answers one call at a time.
+    concurrency = 1;
+    #model;
+    #fields;
+    // key: the column that identifies a row, such as id. fields: the columns
+    // whose text makes the vector, joined by line breaks; a row with none has
+    // no vector.
+    constructor({ model, key, fields, }) {
+        super();
+        this.#model = model;
+        this.key = {
+            name: key,
+            description: `The ${key} of the row the vector is made from.`,
+        };
+        this.#fields = Object.freeze([...fields]);
+        Object.freeze(this);
+    }
+    read(row) {
+        const key = row[this.key.name];
+        if (typeof key !== 'string' && typeof key !== 'number')
+            return null;
+        const text = this.#fields
+            .map((field) => row[field])
+            .filter((value) => typeof value === 'string' && value.trim() !== '')
+            .join('\n');
+        return text === '' ? null : { key: String(key), input: text };
+    }
+    // The model makes every vector, so its provider and id name them all.
+    async identity() {
+        return typeof this.#model === 'string'
+            ? this.#model
+            : `${this.#model.provider}/${this.#model.modelId}`;
+    }
+    async compute(texts, signal) {
+        try {
+            const { embeddings } = await embedMany({
+                model: this.#model,
+                values: [...texts],
+                abortSignal: signal,
+            });
+            return embeddings.map((embedding) => ({
+                value: { vector: unitVector(embedding) },
+            }));
+        }
+        catch (failure) {
+            if (signal?.aborted)
+                return texts.map(() => ({ gone: true }));
+            // A model that refuses a call fails each row of it; the next refresh
+            // asks again.
+            const error = errorMessage(failure);
+            return texts.map(() => ({ error }));
+        }
+    }
+}
+function unitVector(embedding) {
+    const length = Math.hypot(...embedding);
+    return new Uint8Array(Float32Array.from(embedding, (value) => value / length).buffer);
+}

package/package.json

@@ -1,6 +1,52 @@
 {
   "name": "@eltjs/embedding",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
-}
+  "version": "0.1.1",
+  "description": "A rule of an elt computed dataset: it gives each loaded row a vector of its text, made by an AI SDK embedding model, so a search can find rows by meaning.",
+  "license": "Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/ezzabuzaid/elt",
+    "directory": "packages/embedding"
+  },
+  "bugs": {
+    "url": "https://github.com/ezzabuzaid/elt/issues"
+  },
+  "homepage": "https://github.com/ezzabuzaid/elt/tree/main/packages/embedding#readme",
+  "keywords": [
+    "elt",
+    "embedding",
+    "vector",
+    "ai-sdk",
+    "semantic-search"
+  ],
+  "type": "module",
+  "exports": {
+    "./package.json": "./package.json",
+    ".": {
+      "types": "./dist/embedding.d.ts",
+      "default": "./dist/embedding.js"
+    }
+  },
+  "files": [
+    "dist",
+    "!dist/spec/**",
+    "!**/*.tsbuildinfo",
+    "!**/*.test.*"
+  ],
+  "publishConfig": {
+    "access": "public"
+  },
+  "engines": {
+    "node": ">=24"
+  },
+  "dependencies": {
+    "@eltjs/elt": "^0.1.1",
+    "ai": "^7.0.165"
+  },
+  "devDependencies": {
+    "@ai-sdk/provider": "^4.0.37",
+    "@eltjs/elt-sqlite": "^0.1.1",
+    "@zukhruf/sqlite-open": "^0.8.10",
+    "@zukhruf/testing": "^0.8.10"
+  }
+}