feat: add AI knowledge analysis MVP

This commit is contained in:
2026-07-05 00:47:52 -07:00
parent 6aa72d3b43
commit e204974b57
32 changed files with 8705 additions and 4 deletions

View File

@@ -0,0 +1,364 @@
import "server-only";
import { OpenAIEmbeddings } from "@langchain/openai";
import { and, desc, eq, isNull, or, sql } from "drizzle-orm";
import { getAiRuntimeConfig } from "@/modules/ai/server/config";
import type {
AiKnowledgeScope,
KnowledgeEntry,
KnowledgeEntryInput,
KnowledgeRetrievalResult,
} from "@/modules/ai/types";
import { getDatabase } from "@/modules/core/server/db";
import { aiKnowledgeChunks, aiKnowledgeEntries } from "@/modules/core/server/schema";
import type { AuthContext } from "@/modules/core/types";
type KnowledgeRow = typeof aiKnowledgeEntries.$inferSelect;
type ServiceResult<T> = { success: true; data: T } | { success: false; reason: string; status: number };
const CHUNK_TARGET_SIZE = 900;
const CHUNK_OVERLAP_SIZE = 160;
const DEFAULT_RETRIEVAL_LIMIT = 6;
function toIsoString(value: Date): string {
return value.toISOString();
}
function toKnowledgeEntry(row: KnowledgeRow): KnowledgeEntry {
return {
id: row.id,
scope: row.scope,
organizationId: row.organizationId ?? undefined,
title: row.title,
category: row.category,
tags: row.tags,
body: row.body,
status: row.status,
createdAt: toIsoString(row.createdAt),
updatedAt: toIsoString(row.updatedAt),
};
}
function createEmbeddings() {
const configResult = getAiRuntimeConfig();
if (!configResult.success) {
return configResult;
}
const configuration = configResult.config.baseUrl ? { baseURL: configResult.config.baseUrl } : undefined;
return {
success: true as const,
config: configResult.config,
embeddings: new OpenAIEmbeddings({
apiKey: configResult.config.apiKey,
model: configResult.config.embeddingModel,
dimensions: configResult.config.embeddingDimensions,
configuration,
}),
};
}
function chunkKnowledgeText(input: KnowledgeEntryInput): string[] {
const prefix = [input.title, input.category, input.tags].filter(Boolean).join("\n");
const text = `${prefix}\n\n${input.body}`.trim();
if (text.length <= CHUNK_TARGET_SIZE) {
return [text];
}
const chunks: string[] = [];
let start = 0;
while (start < text.length) {
const end = Math.min(start + CHUNK_TARGET_SIZE, text.length);
chunks.push(text.slice(start, end).trim());
if (end >= text.length) {
break;
}
start = Math.max(end - CHUNK_OVERLAP_SIZE, start + 1);
}
return chunks.filter(Boolean);
}
function ensureWritableScope(context: AuthContext, input: KnowledgeEntryInput): ServiceResult<{ organizationId: string | null }> {
if (input.scope === "platform") {
if (!context.permissions.includes("platform:manage")) {
return { success: false, reason: "只有平台管理员可以维护平台知识", status: 403 };
}
return { success: true, data: { organizationId: null } };
}
const organizationId = context.organization?.id;
if (!organizationId) {
return { success: false, reason: "请选择机构后维护知识库", status: 400 };
}
if (input.organizationId && input.organizationId !== organizationId) {
return { success: false, reason: "不能维护其他机构的知识库", status: 403 };
}
return { success: true, data: { organizationId } };
}
function getVisibleKnowledgeWhere(organizationId?: string) {
const platformFilter = and(eq(aiKnowledgeEntries.scope, "platform"), isNull(aiKnowledgeEntries.organizationId));
if (!organizationId) {
return platformFilter;
}
return or(
platformFilter,
and(eq(aiKnowledgeEntries.scope, "organization"), eq(aiKnowledgeEntries.organizationId, organizationId)),
);
}
function getEnabledChunkWhere(organizationId: string) {
return and(
eq(aiKnowledgeEntries.status, "enabled"),
or(
and(eq(aiKnowledgeChunks.scope, "platform"), isNull(aiKnowledgeChunks.organizationId)),
and(eq(aiKnowledgeChunks.scope, "organization"), eq(aiKnowledgeChunks.organizationId, organizationId)),
),
);
}
async function buildKnowledgeChunks(input: KnowledgeEntryInput): Promise<ServiceResult<{ chunks: string[]; vectors: number[][] }>> {
const embeddingsResult = createEmbeddings();
if (!embeddingsResult.success) {
return { success: false, reason: embeddingsResult.reason, status: 500 };
}
const chunks = chunkKnowledgeText(input);
const vectors = await embeddingsResult.embeddings.embedDocuments(chunks);
return { success: true, data: { chunks, vectors } };
}
export async function listKnowledgeEntries(context: AuthContext): Promise<KnowledgeEntry[]> {
const database = getDatabase();
const rows = await database
.select()
.from(aiKnowledgeEntries)
.where(getVisibleKnowledgeWhere(context.organization?.id))
.orderBy(desc(aiKnowledgeEntries.updatedAt));
return rows.map(toKnowledgeEntry);
}
export async function createKnowledgeEntry(
context: AuthContext,
input: KnowledgeEntryInput,
): Promise<ServiceResult<{ entry: KnowledgeEntry }>> {
const scope = ensureWritableScope(context, input);
if (!scope.success) {
return scope;
}
const database = getDatabase();
const build = await buildKnowledgeChunks(input);
if (!build.success) {
return build;
}
const row = await database.transaction(async (transaction) => {
const rows = await transaction
.insert(aiKnowledgeEntries)
.values({
scope: input.scope,
organizationId: scope.data.organizationId,
title: input.title,
category: input.category,
tags: input.tags,
body: input.body,
status: input.status,
createdByAccountId: context.account.id,
updatedByAccountId: context.account.id,
updatedAt: new Date(),
})
.returning();
const entry = rows[0];
if (!entry) {
return null;
}
if (build.data.chunks.length > 0) {
await transaction.insert(aiKnowledgeChunks).values(
build.data.chunks.map((content, index) => ({
entryId: entry.id,
organizationId: entry.organizationId,
scope: entry.scope,
chunkIndex: index,
content,
embedding: build.data.vectors[index] ?? [],
sourceTitle: entry.title,
sourceCategory: entry.category,
})),
);
}
return entry;
});
if (!row) {
return { success: false, reason: "知识库创建失败", status: 500 };
}
return { success: true, data: { entry: toKnowledgeEntry(row) } };
}
async function updateEntryWithChunks(
id: string,
context: AuthContext,
input: KnowledgeEntryInput,
organizationId: string | null,
): Promise<KnowledgeRow | null> {
const build = await buildKnowledgeChunks(input);
if (!build.success) {
throw new Error(build.reason);
}
const database = getDatabase();
return database.transaction(async (transaction) => {
const rows = await transaction
.update(aiKnowledgeEntries)
.set({
scope: input.scope,
organizationId,
title: input.title,
category: input.category,
tags: input.tags,
body: input.body,
status: input.status,
updatedByAccountId: context.account.id,
updatedAt: new Date(),
})
.where(eq(aiKnowledgeEntries.id, id))
.returning();
const row = rows[0];
if (!row) {
return null;
}
await transaction.delete(aiKnowledgeChunks).where(eq(aiKnowledgeChunks.entryId, row.id));
if (build.data.chunks.length > 0) {
await transaction.insert(aiKnowledgeChunks).values(
build.data.chunks.map((content, index) => ({
entryId: row.id,
organizationId: row.organizationId,
scope: row.scope,
chunkIndex: index,
content,
embedding: build.data.vectors[index] ?? [],
sourceTitle: row.title,
sourceCategory: row.category,
})),
);
}
return row;
});
}
export async function updateKnowledgeEntry(
context: AuthContext,
id: string,
input: KnowledgeEntryInput,
): Promise<ServiceResult<{ entry: KnowledgeEntry }>> {
const scope = ensureWritableScope(context, input);
if (!scope.success) {
return scope;
}
const database = getDatabase();
const existingRows = await database
.select()
.from(aiKnowledgeEntries)
.where(and(eq(aiKnowledgeEntries.id, id), getVisibleKnowledgeWhere(context.organization?.id)))
.limit(1);
const existing = existingRows[0];
if (!existing) {
return { success: false, reason: "知识库条目不存在", status: 404 };
}
if (existing.scope === "platform" && !context.permissions.includes("platform:manage")) {
return { success: false, reason: "只有平台管理员可以维护平台知识", status: 403 };
}
let row: KnowledgeRow | null;
try {
row = await updateEntryWithChunks(id, context, input, scope.data.organizationId);
} catch {
return { success: false, reason: "AI_API_KEY 未配置或知识库向量生成失败", status: 500 };
}
if (!row) {
return { success: false, reason: "知识库更新失败", status: 500 };
}
return { success: true, data: { entry: toKnowledgeEntry(row) } };
}
export async function deleteKnowledgeEntry(context: AuthContext, id: string): Promise<ServiceResult<{ entry: KnowledgeEntry }>> {
const database = getDatabase();
const existingRows = await database
.select()
.from(aiKnowledgeEntries)
.where(and(eq(aiKnowledgeEntries.id, id), getVisibleKnowledgeWhere(context.organization?.id)))
.limit(1);
const existing = existingRows[0];
if (!existing) {
return { success: false, reason: "知识库条目不存在", status: 404 };
}
if (existing.scope === "platform" && !context.permissions.includes("platform:manage")) {
return { success: false, reason: "只有平台管理员可以维护平台知识", status: 403 };
}
const rows = await database.delete(aiKnowledgeEntries).where(eq(aiKnowledgeEntries.id, id)).returning();
const row = rows[0];
if (!row) {
return { success: false, reason: "知识库删除失败", status: 500 };
}
return { success: true, data: { entry: toKnowledgeEntry(row) } };
}
export async function retrieveKnowledge(
organizationId: string,
query: string,
options?: { limit?: number },
): Promise<ServiceResult<{ results: KnowledgeRetrievalResult[] }>> {
const embeddingsResult = createEmbeddings();
if (!embeddingsResult.success) {
return { success: false, reason: embeddingsResult.reason, status: 500 };
}
const [embedding] = await embeddingsResult.embeddings.embedDocuments([query]);
if (!embedding) {
return { success: false, reason: "知识库向量生成失败", status: 500 };
}
const database = getDatabase();
const distance = sql<number>`${aiKnowledgeChunks.embedding} <=> ${JSON.stringify(embedding)}::vector`;
const rows = await database
.select({
entryId: aiKnowledgeChunks.entryId,
chunkId: aiKnowledgeChunks.id,
title: aiKnowledgeChunks.sourceTitle,
category: aiKnowledgeChunks.sourceCategory,
content: aiKnowledgeChunks.content,
distance,
})
.from(aiKnowledgeChunks)
.innerJoin(aiKnowledgeEntries, eq(aiKnowledgeEntries.id, aiKnowledgeChunks.entryId))
.where(getEnabledChunkWhere(organizationId))
.orderBy(distance)
.limit(options?.limit ?? DEFAULT_RETRIEVAL_LIMIT);
return {
success: true,
data: {
results: rows.map((row) => ({
entryId: row.entryId,
chunkId: row.chunkId,
title: row.title,
category: row.category,
content: row.content,
score: 1 - row.distance,
})),
},
};
}
export function normalizeKnowledgeScope(scope: AiKnowledgeScope, organizationId?: string): string {
return scope === "platform" ? "platform" : `organization:${organizationId ?? ""}`;
}