p-sw/IdentityDB
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

feat: make FactExtractor extracts multiple facts per input

Browse Source
This commit is contained in:
Shinwoo PARK
2026-05-20 22:59:35 +09:00
parent 188f03e8e8
commit 7602c92046
7 changed files with 157 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

118
tests/ingestion.test.ts
View File

@@ -23,29 +23,31 @@ describe("IdentityDB ingestion", () => {
it("ingests a statement using a provided extractor", async () => {
const extractor: FactExtractor = {
async extract(input) {
return {
statement: input,
topics: [
{
name: "I",
category: "entity",
granularity: "concrete",
role: "subject",
},
{
name: "TypeScript",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "2025",
category: "temporal",
granularity: "concrete",
role: "time",
},
],
};
return [
{
statement: input,
topics: [
{
name: "I",
category: "entity",
granularity: "concrete",
role: "subject",
},
{
name: "TypeScript",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "2025",
category: "temporal",
granularity: "concrete",
role: "time",
},
],
},
];
},
};
@@ -95,39 +97,41 @@ describe("IdentityDB ingestion", () => {
async generateText(input) {
prompt = input;
return {
statement: "I have worked with Bun and TypeScript since 2025.",
summary: "The speaker has Bun and TypeScript experience.",
source: "chat",
confidence: 0.91,
metadata: { channel: "telegram" },
topics: [
{
name: "I",
category: "entity",
granularity: "concrete",
role: "subject",
},
{
name: "Bun",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "TypeScript",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "2025",
category: "temporal",
granularity: "concrete",
role: "time",
},
],
};
return [
{
statement: "I have worked with Bun and TypeScript since 2025.",
summary: "The speaker has Bun and TypeScript experience.",
source: "chat",
confidence: 0.91,
metadata: { channel: "telegram" },
topics: [
{
name: "I",
category: "entity",
granularity: "concrete",
role: "subject",
},
{
name: "Bun",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "TypeScript",
category: "entity",
granularity: "concrete",
role: "object",
},
{
name: "2025",
category: "temporal",
granularity: "concrete",
role: "time",
},
],
},
];
},
},
additionalInstructions: "Prefer technology and time topics.",
@@ -141,7 +145,7 @@ describe("IdentityDB ingestion", () => {
);
expect(prompt).toEqual({
instruction: expect.stringContaining("Extract one structured fact from the user input."),
instruction: expect.stringContaining("Extract structured facts from the user input."),
input: "I have worked with Bun and TypeScript since 2025.",
additionalInstruction: "Prefer technology and time topics.",
});

16
tests/semantic-search.test.ts
View File

@@ -178,13 +178,15 @@ describe('IdentityDB dedup-aware ingestion', () => {
provider = new FakeEmbeddingProvider();
extractor = {
async extract(input) {
return {
statement: input,
topics: [
{ name: 'Bun', category: 'entity', granularity: 'concrete' },
{ name: 'TypeScript', category: 'entity', granularity: 'concrete' },
],
};
return [
{
statement: input,
topics: [
{ name: 'Bun', category: 'entity', granularity: 'concrete' },
{ name: 'TypeScript', category: 'entity', granularity: 'concrete' },
],
},
];
},
};