feat(TRUEREF-0007): implement pluggable embedding generation and vector storage
Add EmbeddingProvider interface with OpenAI-compatible, local (optional @xenova/transformers via dynamic import), and Noop (FTS5-only fallback) implementations. EmbeddingService batches requests and persists Float32Array blobs to snippet_embeddings. GET/PUT /api/v1/settings/embedding endpoints read and write embedding config from the settings table. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
147
src/routes/api/v1/settings/embedding/+server.ts
Normal file
147
src/routes/api/v1/settings/embedding/+server.ts
Normal file
@@ -0,0 +1,147 @@
|
||||
/**
|
||||
* GET /api/v1/settings/embedding — retrieve current embedding configuration
|
||||
* PUT /api/v1/settings/embedding — update embedding configuration
|
||||
*/
|
||||
|
||||
import { json } from '@sveltejs/kit';
|
||||
import type { RequestHandler } from './$types';
|
||||
import { getClient } from '$lib/server/db/client';
|
||||
import {
|
||||
EMBEDDING_CONFIG_KEY,
|
||||
createProviderFromConfig,
|
||||
defaultEmbeddingConfig,
|
||||
type EmbeddingConfig
|
||||
} from '$lib/server/embeddings/factory';
|
||||
import { handleServiceError, InvalidInputError } from '$lib/server/utils/validation';
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Helpers
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
function readConfig(db: ReturnType<typeof getClient>): EmbeddingConfig {
|
||||
const row = db
|
||||
.prepare(`SELECT value FROM settings WHERE key = ?`)
|
||||
.get(EMBEDDING_CONFIG_KEY) as { value: string } | undefined;
|
||||
|
||||
if (!row) return defaultEmbeddingConfig();
|
||||
|
||||
try {
|
||||
return JSON.parse(row.value) as EmbeddingConfig;
|
||||
} catch {
|
||||
return defaultEmbeddingConfig();
|
||||
}
|
||||
}
|
||||
|
||||
function validateConfig(body: unknown): EmbeddingConfig {
|
||||
if (typeof body !== 'object' || body === null) {
|
||||
throw new InvalidInputError('Request body must be a JSON object');
|
||||
}
|
||||
|
||||
const obj = body as Record<string, unknown>;
|
||||
|
||||
const provider = obj.provider;
|
||||
if (provider !== 'openai' && provider !== 'local' && provider !== 'none') {
|
||||
throw new InvalidInputError(
|
||||
`Invalid provider "${String(provider)}". Must be one of: openai, local, none.`
|
||||
);
|
||||
}
|
||||
|
||||
if (provider === 'openai') {
|
||||
const openai = obj.openai as Record<string, unknown> | undefined;
|
||||
if (!openai || typeof openai !== 'object') {
|
||||
throw new InvalidInputError('openai config object is required when provider is "openai"');
|
||||
}
|
||||
if (typeof openai.baseUrl !== 'string' || !openai.baseUrl) {
|
||||
throw new InvalidInputError('openai.baseUrl must be a non-empty string');
|
||||
}
|
||||
if (typeof openai.apiKey !== 'string' || !openai.apiKey) {
|
||||
throw new InvalidInputError('openai.apiKey must be a non-empty string');
|
||||
}
|
||||
if (typeof openai.model !== 'string' || !openai.model) {
|
||||
throw new InvalidInputError('openai.model must be a non-empty string');
|
||||
}
|
||||
|
||||
const config: EmbeddingConfig = {
|
||||
provider: 'openai',
|
||||
openai: {
|
||||
baseUrl: openai.baseUrl as string,
|
||||
apiKey: openai.apiKey as string,
|
||||
model: openai.model as string,
|
||||
dimensions:
|
||||
typeof openai.dimensions === 'number' ? (openai.dimensions as number) : undefined,
|
||||
maxBatchSize:
|
||||
typeof openai.maxBatchSize === 'number'
|
||||
? (openai.maxBatchSize as number)
|
||||
: undefined
|
||||
}
|
||||
};
|
||||
return config;
|
||||
}
|
||||
|
||||
return { provider: provider as 'local' | 'none' };
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// GET
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
export const GET: RequestHandler = () => {
|
||||
try {
|
||||
const db = getClient();
|
||||
const config = readConfig(db);
|
||||
|
||||
// Strip the apiKey from the response for security.
|
||||
const safeConfig = sanitizeForResponse(config);
|
||||
return json(safeConfig);
|
||||
} catch (err) {
|
||||
return handleServiceError(err);
|
||||
}
|
||||
};
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// PUT
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
export const PUT: RequestHandler = async ({ request }) => {
|
||||
try {
|
||||
const body = await request.json();
|
||||
const config = validateConfig(body);
|
||||
|
||||
// Verify provider connectivity before persisting (skip for noop).
|
||||
if (config.provider !== 'none') {
|
||||
const provider = createProviderFromConfig(config);
|
||||
const available = await provider.isAvailable();
|
||||
if (!available) {
|
||||
throw new InvalidInputError(
|
||||
`Could not connect to the "${config.provider}" embedding provider. Check your configuration.`
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const db = getClient();
|
||||
db.prepare(
|
||||
`INSERT INTO settings (key, value, updated_at)
|
||||
VALUES (?, ?, unixepoch())
|
||||
ON CONFLICT (key) DO UPDATE SET value = excluded.value, updated_at = excluded.updated_at`
|
||||
).run(EMBEDDING_CONFIG_KEY, JSON.stringify(config));
|
||||
|
||||
const safeConfig = sanitizeForResponse(config);
|
||||
return json(safeConfig);
|
||||
} catch (err) {
|
||||
return handleServiceError(err);
|
||||
}
|
||||
};
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Sanitize — remove sensitive fields before returning to clients
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
function sanitizeForResponse(config: EmbeddingConfig): Omit<EmbeddingConfig, 'openai'> & {
|
||||
openai?: Omit<NonNullable<EmbeddingConfig['openai']>, 'apiKey'>;
|
||||
} {
|
||||
if (config.provider === 'openai' && config.openai) {
|
||||
const { apiKey: _apiKey, ...rest } = config.openai;
|
||||
return { ...config, openai: rest };
|
||||
}
|
||||
return config;
|
||||
}
|
||||
Reference in New Issue
Block a user