chore(FEEDBACK-0001): linting
This commit is contained in:
Giancarmine Salucci
@@ -34,18 +34,18 @@ Implement a pluggable embedding generation system that produces vector represent
|
||||
// src/lib/server/embeddings/provider.ts
|
||||
|
||||
export interface EmbeddingVector {
|
||||
values: Float32Array;
|
||||
dimensions: number;
|
||||
model: string;
|
||||
values: Float32Array;
|
||||
dimensions: number;
|
||||
model: string;
|
||||
}
|
||||
|
||||
export interface EmbeddingProvider {
|
||||
readonly name: string;
|
||||
readonly dimensions: number;
|
||||
readonly model: string;
|
||||
readonly name: string;
|
||||
readonly dimensions: number;
|
||||
readonly model: string;
|
||||
|
||||
embed(texts: string[]): Promise<EmbeddingVector[]>;
|
||||
isAvailable(): Promise<boolean>;
|
||||
embed(texts: string[]): Promise<EmbeddingVector[]>;
|
||||
isAvailable(): Promise<boolean>;
|
||||
}
|
||||
```
|
||||
|
||||
@@ -55,51 +55,51 @@ export interface EmbeddingProvider {
|
||||
|
||||
```typescript
|
||||
export interface OpenAIProviderConfig {
|
||||
baseUrl: string; // e.g. "https://api.openai.com/v1" or "http://localhost:11434/v1"
|
||||
apiKey: string;
|
||||
model: string; // e.g. "text-embedding-3-small", "nomic-embed-text"
|
||||
dimensions?: number; // override for models that support it (e.g. text-embedding-3-small)
|
||||
maxBatchSize?: number; // default: 100
|
||||
baseUrl: string; // e.g. "https://api.openai.com/v1" or "http://localhost:11434/v1"
|
||||
apiKey: string;
|
||||
model: string; // e.g. "text-embedding-3-small", "nomic-embed-text"
|
||||
dimensions?: number; // override for models that support it (e.g. text-embedding-3-small)
|
||||
maxBatchSize?: number; // default: 100
|
||||
}
|
||||
|
||||
export class OpenAIEmbeddingProvider implements EmbeddingProvider {
|
||||
constructor(private config: OpenAIProviderConfig) {}
|
||||
constructor(private config: OpenAIProviderConfig) {}
|
||||
|
||||
async embed(texts: string[]): Promise<EmbeddingVector[]> {
|
||||
// Batch into groups of maxBatchSize
|
||||
const batches = chunk(texts, this.config.maxBatchSize ?? 100);
|
||||
const allEmbeddings: EmbeddingVector[] = [];
|
||||
async embed(texts: string[]): Promise<EmbeddingVector[]> {
|
||||
// Batch into groups of maxBatchSize
|
||||
const batches = chunk(texts, this.config.maxBatchSize ?? 100);
|
||||
const allEmbeddings: EmbeddingVector[] = [];
|
||||
|
||||
for (const batch of batches) {
|
||||
const response = await fetch(`${this.config.baseUrl}/embeddings`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Authorization': `Bearer ${this.config.apiKey}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.config.model,
|
||||
input: batch,
|
||||
dimensions: this.config.dimensions,
|
||||
}),
|
||||
});
|
||||
for (const batch of batches) {
|
||||
const response = await fetch(`${this.config.baseUrl}/embeddings`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
Authorization: `Bearer ${this.config.apiKey}`,
|
||||
'Content-Type': 'application/json'
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.config.model,
|
||||
input: batch,
|
||||
dimensions: this.config.dimensions
|
||||
})
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new EmbeddingError(`API error: ${response.status}`);
|
||||
}
|
||||
if (!response.ok) {
|
||||
throw new EmbeddingError(`API error: ${response.status}`);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
for (const item of data.data) {
|
||||
allEmbeddings.push({
|
||||
values: new Float32Array(item.embedding),
|
||||
dimensions: item.embedding.length,
|
||||
model: this.config.model,
|
||||
});
|
||||
}
|
||||
}
|
||||
const data = await response.json();
|
||||
for (const item of data.data) {
|
||||
allEmbeddings.push({
|
||||
values: new Float32Array(item.embedding),
|
||||
dimensions: item.embedding.length,
|
||||
model: this.config.model
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return allEmbeddings;
|
||||
}
|
||||
return allEmbeddings;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -110,41 +110,41 @@ export class OpenAIEmbeddingProvider implements EmbeddingProvider {
|
||||
```typescript
|
||||
// Uses @xenova/transformers — only loaded if installed
|
||||
export class LocalEmbeddingProvider implements EmbeddingProvider {
|
||||
private pipeline: unknown = null;
|
||||
private pipeline: unknown = null;
|
||||
|
||||
readonly name = 'local';
|
||||
readonly model = 'Xenova/all-MiniLM-L6-v2'; // 384-dim, fast, small
|
||||
readonly dimensions = 384;
|
||||
readonly name = 'local';
|
||||
readonly model = 'Xenova/all-MiniLM-L6-v2'; // 384-dim, fast, small
|
||||
readonly dimensions = 384;
|
||||
|
||||
async embed(texts: string[]): Promise<EmbeddingVector[]> {
|
||||
if (!this.pipeline) {
|
||||
const { pipeline } = await import('@xenova/transformers');
|
||||
this.pipeline = await pipeline('feature-extraction', this.model);
|
||||
}
|
||||
async embed(texts: string[]): Promise<EmbeddingVector[]> {
|
||||
if (!this.pipeline) {
|
||||
const { pipeline } = await import('@xenova/transformers');
|
||||
this.pipeline = await pipeline('feature-extraction', this.model);
|
||||
}
|
||||
|
||||
const results: EmbeddingVector[] = [];
|
||||
for (const text of texts) {
|
||||
const output = await (this.pipeline as Function)(text, {
|
||||
pooling: 'mean',
|
||||
normalize: true,
|
||||
});
|
||||
results.push({
|
||||
values: new Float32Array(output.data),
|
||||
dimensions: this.dimensions,
|
||||
model: this.model,
|
||||
});
|
||||
}
|
||||
return results;
|
||||
}
|
||||
const results: EmbeddingVector[] = [];
|
||||
for (const text of texts) {
|
||||
const output = await (this.pipeline as Function)(text, {
|
||||
pooling: 'mean',
|
||||
normalize: true
|
||||
});
|
||||
results.push({
|
||||
values: new Float32Array(output.data),
|
||||
dimensions: this.dimensions,
|
||||
model: this.model
|
||||
});
|
||||
}
|
||||
return results;
|
||||
}
|
||||
|
||||
async isAvailable(): Promise<boolean> {
|
||||
try {
|
||||
await import('@xenova/transformers');
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
async isAvailable(): Promise<boolean> {
|
||||
try {
|
||||
await import('@xenova/transformers');
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -154,53 +154,55 @@ export class LocalEmbeddingProvider implements EmbeddingProvider {
|
||||
|
||||
```typescript
|
||||
export class EmbeddingService {
|
||||
constructor(
|
||||
private db: BetterSQLite3.Database,
|
||||
private provider: EmbeddingProvider
|
||||
) {}
|
||||
constructor(
|
||||
private db: BetterSQLite3.Database,
|
||||
private provider: EmbeddingProvider
|
||||
) {}
|
||||
|
||||
async embedSnippets(
|
||||
snippetIds: string[],
|
||||
onProgress?: (done: number, total: number) => void
|
||||
): Promise<void> {
|
||||
const snippets = this.db.prepare(
|
||||
`SELECT id, content, type FROM snippets WHERE id IN (${snippetIds.map(() => '?').join(',')})`
|
||||
).all(...snippetIds) as Snippet[];
|
||||
async embedSnippets(
|
||||
snippetIds: string[],
|
||||
onProgress?: (done: number, total: number) => void
|
||||
): Promise<void> {
|
||||
const snippets = this.db
|
||||
.prepare(
|
||||
`SELECT id, content, type FROM snippets WHERE id IN (${snippetIds.map(() => '?').join(',')})`
|
||||
)
|
||||
.all(...snippetIds) as Snippet[];
|
||||
|
||||
// Prepare text for embedding: combine title + content
|
||||
const texts = snippets.map(s =>
|
||||
[s.title, s.breadcrumb, s.content].filter(Boolean).join('\n').slice(0, 2048)
|
||||
);
|
||||
// Prepare text for embedding: combine title + content
|
||||
const texts = snippets.map((s) =>
|
||||
[s.title, s.breadcrumb, s.content].filter(Boolean).join('\n').slice(0, 2048)
|
||||
);
|
||||
|
||||
const BATCH_SIZE = 50;
|
||||
const insert = this.db.prepare(`
|
||||
const BATCH_SIZE = 50;
|
||||
const insert = this.db.prepare(`
|
||||
INSERT OR REPLACE INTO snippet_embeddings (snippet_id, model, dimensions, embedding, created_at)
|
||||
VALUES (?, ?, ?, ?, unixepoch())
|
||||
`);
|
||||
|
||||
for (let i = 0; i < snippets.length; i += BATCH_SIZE) {
|
||||
const batch = snippets.slice(i, i + BATCH_SIZE);
|
||||
const batchTexts = texts.slice(i, i + BATCH_SIZE);
|
||||
for (let i = 0; i < snippets.length; i += BATCH_SIZE) {
|
||||
const batch = snippets.slice(i, i + BATCH_SIZE);
|
||||
const batchTexts = texts.slice(i, i + BATCH_SIZE);
|
||||
|
||||
const embeddings = await this.provider.embed(batchTexts);
|
||||
const embeddings = await this.provider.embed(batchTexts);
|
||||
|
||||
const insertMany = this.db.transaction(() => {
|
||||
for (let j = 0; j < batch.length; j++) {
|
||||
const snippet = batch[j];
|
||||
const embedding = embeddings[j];
|
||||
insert.run(
|
||||
snippet.id,
|
||||
embedding.model,
|
||||
embedding.dimensions,
|
||||
Buffer.from(embedding.values.buffer)
|
||||
);
|
||||
}
|
||||
});
|
||||
insertMany();
|
||||
const insertMany = this.db.transaction(() => {
|
||||
for (let j = 0; j < batch.length; j++) {
|
||||
const snippet = batch[j];
|
||||
const embedding = embeddings[j];
|
||||
insert.run(
|
||||
snippet.id,
|
||||
embedding.model,
|
||||
embedding.dimensions,
|
||||
Buffer.from(embedding.values.buffer)
|
||||
);
|
||||
}
|
||||
});
|
||||
insertMany();
|
||||
|
||||
onProgress?.(Math.min(i + BATCH_SIZE, snippets.length), snippets.length);
|
||||
}
|
||||
}
|
||||
onProgress?.(Math.min(i + BATCH_SIZE, snippets.length), snippets.length);
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -212,13 +214,13 @@ Stored in the `settings` table as JSON:
|
||||
|
||||
```typescript
|
||||
export interface EmbeddingConfig {
|
||||
provider: 'openai' | 'local' | 'none';
|
||||
openai?: {
|
||||
baseUrl: string;
|
||||
apiKey: string;
|
||||
model: string;
|
||||
dimensions?: number;
|
||||
};
|
||||
provider: 'openai' | 'local' | 'none';
|
||||
openai?: {
|
||||
baseUrl: string;
|
||||
apiKey: string;
|
||||
model: string;
|
||||
dimensions?: number;
|
||||
};
|
||||
}
|
||||
|
||||
// Settings key: 'embedding_config'
|
||||
@@ -227,14 +229,15 @@ export interface EmbeddingConfig {
|
||||
### API Endpoints
|
||||
|
||||
`GET /api/v1/settings/embedding`
|
||||
|
||||
```json
|
||||
{
|
||||
"provider": "openai",
|
||||
"openai": {
|
||||
"baseUrl": "https://api.openai.com/v1",
|
||||
"model": "text-embedding-3-small",
|
||||
"dimensions": 1536
|
||||
}
|
||||
"provider": "openai",
|
||||
"openai": {
|
||||
"baseUrl": "https://api.openai.com/v1",
|
||||
"model": "text-embedding-3-small",
|
||||
"dimensions": 1536
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -251,11 +254,7 @@ Embeddings are stored as raw `Float32Array` binary blobs:
|
||||
const buffer = Buffer.from(float32Array.buffer);
|
||||
|
||||
// Retrieve
|
||||
const float32Array = new Float32Array(
|
||||
buffer.buffer,
|
||||
buffer.byteOffset,
|
||||
buffer.byteLength / 4
|
||||
);
|
||||
const float32Array = new Float32Array(buffer.buffer, buffer.byteOffset, buffer.byteLength / 4);
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
Reference in New Issue
Block a user