Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: do not return false immediately with negative operators #1058

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

fix: do not return false immediately with negative operators #1058

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 22 additions & 6 deletions packages/llamaindex/src/storage/vectorStore/SimpleVectorStore.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,23 +62,32 @@ const OPERATOR_TO_FILTER: {
return parseArrayValue(value).every((v) => metadata[key].includes(v));
},
[FilterOperator.TEXT_MATCH]: ({ key, value }, metadata) => {
return metadata[key].includes(parsePrimitiveValue(value));
if (typeof metadata[key] !== "string") return false;
return metadata[key].includes(parsePrimitiveValue(value).toString());
},
[FilterOperator.CONTAINS]: ({ key, value }, metadata) => {
if (!Array.isArray(metadata[key])) return false;
return !!parseArrayValue(metadata[key]).find((v) => v === value);
},
[FilterOperator.GT]: ({ key, value }, metadata) => {
return metadata[key] > parsePrimitiveValue(value);
const val = metadata[key];
if (typeof val !== "string" && typeof val !== "number") return false;
return val > parsePrimitiveValue(value);
},
[FilterOperator.LT]: ({ key, value }, metadata) => {
return metadata[key] < parsePrimitiveValue(value);
const val = metadata[key];
if (typeof val !== "string" && typeof val !== "number") return false;
return val < parsePrimitiveValue(value);
},
[FilterOperator.GTE]: ({ key, value }, metadata) => {
return metadata[key] >= parsePrimitiveValue(value);
const val = metadata[key];
if (typeof val !== "string" && typeof val !== "number") return false;
return val >= parsePrimitiveValue(value);
},
[FilterOperator.LTE]: ({ key, value }, metadata) => {
return metadata[key] <= parsePrimitiveValue(value);
const val = metadata[key];
if (typeof val !== "string" && typeof val !== "number") return false;
return val <= parsePrimitiveValue(value);
},
};

Expand All @@ -94,7 +103,14 @@ const buildFilterFn = (
const queryCondition = condition || "and"; // default to and

const itemFilterFn = (filter: MetadataFilter): boolean => {
if (metadata[filter.key] === undefined) return false; // always return false if the metadata key is not present
// for all operators except != and nin, if the metadata key is not present, return false
if (
metadata[filter.key] === undefined &&
filter.operator !== FilterOperator.NE &&
filter.operator !== FilterOperator.NIN
) {
return false;
}
const metadataLookupFn = OPERATOR_TO_FILTER[filter.operator];
if (!metadataLookupFn)
throw new Error(`Unsupported operator: ${filter.operator}`);
Expand Down
188 changes: 175 additions & 13 deletions packages/llamaindex/tests/vectorStores/SimpleVectorStore.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ describe("SimpleVectorStore", () => {
private: "true",
weight: 1.2,
type: ["husky", "puppy"],
height: 50,
},
}),
new TextNode({
Expand Down Expand Up @@ -87,19 +88,6 @@ describe("SimpleVectorStore", () => {
title: "No filter",
expected: 3,
},
{
title: "Filter with non-exist key",
filters: {
filters: [
{
key: "non-exist-key",
value: "cat",
operator: "==",
},
],
},
expected: 0,
},
{
title: "Filter EQ",
filters: {
Expand Down Expand Up @@ -309,4 +297,178 @@ describe("SimpleVectorStore", () => {
});
});
});

describe("[SimpleVectorStore] query nodes with optional key in metadata", () => {
const testcases: FilterTestCase[] = [
{
title: "Filter EQ with an optional key",
filters: {
filters: [
{
key: "height",
value: 50,
operator: "==",
},
],
},
expected: 1,
},
{
title: "Filter NE with an optional key",
filters: {
filters: [
{
key: "height",
value: 50,
operator: "!=",
},
],
},
expected: 2,
},
{
title: "Filter GT with an optional key",
filters: {
filters: [
{
key: "height",
value: 48,
operator: ">",
},
],
},
expected: 1,
},
{
title: "Filter GTE with an optional key",
filters: {
filters: [
{
key: "height",
value: 50,
operator: ">=",
},
],
},
expected: 1,
},
{
title: "Filter LT with an optional key",
filters: {
filters: [
{
key: "height",
value: 50,
operator: "<",
},
],
},
expected: 0,
},
{
title: "Filter LTE with an optional key",
filters: {
filters: [
{
key: "height",
value: 50,
operator: "<=",
},
],
},
expected: 1,
},
{
title: "Filter IN with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: ["a", "b"],
operator: "in",
},
],
},
expected: 0,
},
{
title: "Filter NIN with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: ["a", "b"],
operator: "nin",
},
],
},
expected: 3,
},
{
title: "Filter ANY with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: ["a", "b"],
operator: "any",
},
],
},
expected: 0,
},
{
title: "Filter ALL with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: ["a", "b"],
operator: "all",
},
],
},
expected: 0,
},
{
title: "Filter CONTAINS with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: "a",
operator: "contains",
},
],
},
expected: 0,
},
{
title: "Filter TEXT_MATCH with an optional key",
filters: {
filters: [
{
key: "non-existing-key",
value: "a",
operator: "text_match",
},
],
},
expected: 0,
},
];

testcases.forEach((tc) => {
it(`[${tc.title}] should return ${tc.expected} nodes`, async () => {
await store.add(nodes);
const result = await store.query({
queryEmbedding: [0.1, 0.2],
similarityTopK: 3,
mode: VectorStoreQueryMode.DEFAULT,
filters: tc.filters,
});
expect(result.ids).length(tc.expected);
});
});
});
});