d25d482dc2
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
Publish CLI Package / publish-npm (push) Has been cancelled
Publish Python SDK / publish-pypi (push) Has been cancelled
Publish TypeScript SDK / publish-npm (push) Has been cancelled
175 lines
5.4 KiB
TypeScript
175 lines
5.4 KiB
TypeScript
import { z } from 'zod'
|
||
import {
|
||
knowledgeBaseParamsSchema,
|
||
nullableWireDateSchema,
|
||
successResponseSchema,
|
||
wireDateSchema,
|
||
} from '@/lib/api/contracts/knowledge/shared'
|
||
import { defineRouteContract } from '@/lib/api/contracts/types'
|
||
import type { StrategyOptions } from '@/lib/chunkers/types'
|
||
import { KNOWLEDGE_BASE_DESCRIPTION_MAX_LENGTH } from '@/lib/knowledge/constants'
|
||
|
||
export const knowledgeScopeSchema = z.enum(['active', 'archived', 'all'])
|
||
export type KnowledgeScope = z.output<typeof knowledgeScopeSchema>
|
||
|
||
export const listKnowledgeBasesQuerySchema = z.object({
|
||
workspaceId: z.string().min(1).optional(),
|
||
scope: knowledgeScopeSchema.default('active'),
|
||
})
|
||
|
||
export const chunkingStrategyOptionsSchema = z
|
||
.object({
|
||
pattern: z.string().max(500).optional(),
|
||
separators: z.array(z.string()).optional(),
|
||
recipe: z.enum(['plain', 'markdown', 'code']).optional(),
|
||
strictBoundaries: z.boolean().optional(),
|
||
})
|
||
.strict() satisfies z.ZodType<StrategyOptions>
|
||
|
||
export const chunkingConfigSchema = z
|
||
.object({
|
||
maxSize: z.number().min(100).max(4000),
|
||
minSize: z.number().min(1).max(2000),
|
||
overlap: z.number().min(0).max(500),
|
||
strategy: z.enum(['auto', 'text', 'regex', 'recursive', 'sentence', 'token']).optional(),
|
||
strategyOptions: chunkingStrategyOptionsSchema.optional(),
|
||
})
|
||
.refine((data) => data.minSize < data.maxSize * 4, {
|
||
message: 'Min chunk size (characters) must be less than max chunk size (tokens × 4)',
|
||
})
|
||
.refine((data) => data.overlap < data.maxSize, {
|
||
message: 'Overlap must be less than max chunk size',
|
||
})
|
||
.refine(
|
||
(data) => data.strategy !== 'regex' || typeof data.strategyOptions?.pattern === 'string',
|
||
{
|
||
message: 'Regex pattern is required when using the regex chunking strategy',
|
||
}
|
||
)
|
||
.refine((data) => data.strategy === 'regex' || data.strategyOptions?.strictBoundaries !== true, {
|
||
message: 'strictBoundaries is only valid for the regex chunking strategy',
|
||
})
|
||
|
||
export const createKnowledgeBaseBodySchema = z.object({
|
||
name: z.string().min(1, 'Name is required'),
|
||
description: z
|
||
.string()
|
||
.max(
|
||
KNOWLEDGE_BASE_DESCRIPTION_MAX_LENGTH,
|
||
`Description must be ${KNOWLEDGE_BASE_DESCRIPTION_MAX_LENGTH} characters or less`
|
||
)
|
||
.optional(),
|
||
workspaceId: z.string().min(1, 'Workspace ID is required'),
|
||
embeddingModel: z.literal('text-embedding-3-small').default('text-embedding-3-small'),
|
||
embeddingDimension: z.literal(1536).default(1536),
|
||
chunkingConfig: chunkingConfigSchema.default({
|
||
maxSize: 1024,
|
||
minSize: 100,
|
||
overlap: 200,
|
||
}),
|
||
})
|
||
|
||
export const updateKnowledgeBaseBodySchema = createKnowledgeBaseBodySchema
|
||
.pick({
|
||
name: true,
|
||
description: true,
|
||
})
|
||
.partial()
|
||
.extend({
|
||
chunkingConfig: chunkingConfigSchema.optional(),
|
||
workspaceId: z.string().nullable().optional(),
|
||
embeddingModel: z.literal('text-embedding-3-small').optional(),
|
||
embeddingDimension: z.literal(1536).optional(),
|
||
})
|
||
|
||
const knowledgeChunkingConfigSchema = z
|
||
.object({
|
||
maxSize: z.number(),
|
||
minSize: z.number(),
|
||
overlap: z.number(),
|
||
strategy: z.enum(['auto', 'text', 'regex', 'recursive', 'sentence', 'token']).optional(),
|
||
strategyOptions: chunkingStrategyOptionsSchema.optional(),
|
||
})
|
||
.passthrough()
|
||
|
||
export const knowledgeBaseDataSchema = z
|
||
.object({
|
||
id: z.string(),
|
||
userId: z.string(),
|
||
name: z.string(),
|
||
description: z.string().nullable(),
|
||
tokenCount: z.number(),
|
||
embeddingModel: z.string(),
|
||
embeddingDimension: z.number(),
|
||
chunkingConfig: knowledgeChunkingConfigSchema,
|
||
createdAt: wireDateSchema,
|
||
updatedAt: wireDateSchema,
|
||
deletedAt: nullableWireDateSchema,
|
||
workspaceId: z.string().nullable(),
|
||
docCount: z.number().optional(),
|
||
connectorTypes: z.array(z.string()).optional(),
|
||
})
|
||
.passthrough()
|
||
export type KnowledgeBaseData = z.output<typeof knowledgeBaseDataSchema>
|
||
|
||
export const listKnowledgeBasesContract = defineRouteContract({
|
||
method: 'GET',
|
||
path: '/api/knowledge',
|
||
query: listKnowledgeBasesQuerySchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: successResponseSchema(z.array(knowledgeBaseDataSchema)),
|
||
},
|
||
})
|
||
|
||
export const createKnowledgeBaseContract = defineRouteContract({
|
||
method: 'POST',
|
||
path: '/api/knowledge',
|
||
body: createKnowledgeBaseBodySchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: successResponseSchema(knowledgeBaseDataSchema),
|
||
},
|
||
})
|
||
|
||
export const getKnowledgeBaseContract = defineRouteContract({
|
||
method: 'GET',
|
||
path: '/api/knowledge/[id]',
|
||
params: knowledgeBaseParamsSchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: successResponseSchema(knowledgeBaseDataSchema),
|
||
},
|
||
})
|
||
|
||
export const updateKnowledgeBaseContract = defineRouteContract({
|
||
method: 'PUT',
|
||
path: '/api/knowledge/[id]',
|
||
params: knowledgeBaseParamsSchema,
|
||
body: updateKnowledgeBaseBodySchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: successResponseSchema(knowledgeBaseDataSchema),
|
||
},
|
||
})
|
||
|
||
export const deleteKnowledgeBaseContract = defineRouteContract({
|
||
method: 'DELETE',
|
||
path: '/api/knowledge/[id]',
|
||
params: knowledgeBaseParamsSchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: successResponseSchema(z.object({ message: z.string() })),
|
||
},
|
||
})
|
||
|
||
export const restoreKnowledgeBaseContract = defineRouteContract({
|
||
method: 'POST',
|
||
path: '/api/knowledge/[id]/restore',
|
||
params: knowledgeBaseParamsSchema,
|
||
response: {
|
||
mode: 'json',
|
||
schema: z.object({ success: z.literal(true) }).passthrough(),
|
||
},
|
||
})
|