Compare commits

...

12 Commits

Author SHA1 Message Date
github-actions[bot] 8b95abdc85 Release 0.5.26 (#1193)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-12 11:38:07 -07:00
Alex Yang ffe0cd1ef1 chore: update changelog 2024-09-12 11:33:32 -07:00
Alex Yang 5d2111a19f feat: init support openai o1 model (#1192) 2024-09-12 11:31:05 -07:00
Alex Yang 68ac7fd57f ci: fix syntax (#1186) 2024-09-11 16:54:39 -07:00
Alex Yang 7320d96a36 fix: waku build (#1185) 2024-09-11 15:36:39 -07:00
Goran ee17fb475b feat: add PostgreSQL storage (#1180) 2024-09-11 12:31:04 -07:00
github-actions[bot] 28b877e31f Release 0.5.25 (#1182)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-11 12:08:39 -07:00
Alex Yang 4389b80a52 docs: update README.md (#1183) 2024-09-11 11:07:00 -07:00
Alex Yang d3bc663951 fix: vector store cleanup (#1175) 2024-09-11 10:20:55 -07:00
Kieran Simkin 4810364788 fix: handle RouterQueryEngine with string query (#1181) 2024-09-11 10:19:59 -07:00
github-actions[bot] 2dcad52dd9 Release 0.5.24 (#1178)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-10 23:48:51 -07:00
Alex Yang 0bf8d80b12 fix: llama cloud api build 2024-09-10 23:39:58 -07:00
65 changed files with 972 additions and 134 deletions
+15 -4
View File
@@ -12,6 +12,10 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
POSTGRES_USER: runneradmin
POSTGRES_HOST_AUTH_METHOD: trust
jobs:
e2e:
strategy:
@@ -22,9 +26,17 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres@v1
with:
database: llamaindex_node_test
dev-files: true
- run: |
cd /tmp
git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
cd pgvector
make
sudo make install
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
@@ -42,7 +54,6 @@ jobs:
node-version: [18.x, 20.x, 22.x]
name: Test on Node.js ${{ matrix.node-version }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
@@ -92,7 +103,7 @@ jobs:
- nextjs-agent
- nextjs-edge-runtime
- nextjs-node-runtime
# - waku-query-engine
- waku-query-engine
runs-on: ubuntu-latest
name: Build LlamaIndex Example (${{ matrix.packages }})
steps:
+51 -1
View File
@@ -36,9 +36,44 @@ For now, browser support is limited due to the lack of support for [AsyncLocalSt
npm install llamaindex
pnpm install llamaindex
yarn add llamaindex
jsr install @llamaindex/core
```
### Setup TypeScript
```json5
{
compilerOptions: {
// ⬇️ add this line to your tsconfig.json
moduleResolution: "bundler", // or "node16"
},
}
```
<details>
<summary>Why?</summary>
We are shipping both ESM and CJS module, and compatible with Vercel Edge, Cloudflare Workers, and other serverless platforms.
So we are using [conditional exports](https://nodejs.org/api/packages.html#conditional-exports) to support all environments.
This is a kind of modern way of shipping packages, but might cause TypeScript type check to fail because of legacy module resolution.
Imaging you put output file into `/dist/openai.js` but you are importing `llamaindex/openai` in your code, and set `package.json` like this:
```json
{
"exports": {
"./openai": "./dist/openai.js"
}
}
```
In old module resolution, TypeScript will not be able to find the module because it is not follow the file structure, even you run `node index.js` successfully. (on Node.js >=16)
See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) or
[TypeScript 5.0 blog](https://devblogs.microsoft.com/typescript/announcing-typescript-5-0/#--moduleresolution-bundler7).
</details>
### Node.js
```ts
@@ -154,6 +189,21 @@ export async function chatWithAgent(
}
```
### Vite
We have some wasm dependencies for better performance. You can use `vite-plugin-wasm` to load them.
```ts
import wasm from "vite-plugin-wasm";
export default {
plugins: [wasm()],
ssr: {
external: ["tiktoken"],
},
};
```
## Playground
Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
+22
View File
@@ -1,5 +1,27 @@
# docs
## 0.0.67
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.0.66
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.0.65
### Patch Changes
- llamaindex@0.5.24
## 0.0.64
### Patch Changes
+37 -3
View File
@@ -4,12 +4,19 @@ sidebar_position: 7
# Storage
Storage in LlamaIndex.TS works automatically once you've configured a `StorageContext` object. Just configure the `persistDir` and attach it to an index.
Storage in LlamaIndex.TS works automatically once you've configured a
`StorageContext` object.
Right now, only saving and loading from disk is supported, with future integrations planned!
## Local Storage
You can configure the `persistDir` and attach it to an index.
```typescript
import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
import {
Document,
VectorStoreIndex,
storageContextFromDefaults,
} from "llamaindex";
const storageContext = await storageContextFromDefaults({
persistDir: "./storage",
@@ -21,6 +28,33 @@ const index = await VectorStoreIndex.fromDocuments([document], {
});
```
## PostgreSQL Storage
You can configure the `schemaName`, `tableName`, `namespace`, and
`connectionString`. If a `connectionString` is not
provided, it will use the environment variables `PGHOST`, `PGUSER`,
`PGPASSWORD`, `PGDATABASE` and `PGPORT`.
```typescript
import {
Document,
VectorStoreIndex,
PostgresDocumentStore,
PostgresIndexStore,
storageContextFromDefaults,
} from "llamaindex";
const storageContext = await storageContextFromDefaults({
docStore: new PostgresDocumentStore(),
indexStore: new PostgresIndexStore(),
});
const document = new Document({ text: "Test Text" });
const index = await VectorStoreIndex.fromDocuments([document], {
storageContext,
});
```
## API Reference
- [StorageContext](../api/interfaces/StorageContext.md)
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "docs",
"version": "0.0.64",
"version": "0.0.67",
"private": true,
"scripts": {
"docusaurus": "docusaurus",
@@ -1,5 +1,30 @@
# @llamaindex/autotool-01-node-example
## 0.0.7
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
- @llamaindex/autotool@2.0.1
## 0.0.6
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
- @llamaindex/autotool@2.0.1
## 0.0.5
### Patch Changes
- llamaindex@0.5.24
- @llamaindex/autotool@2.0.1
## 0.0.4
### Patch Changes
@@ -13,5 +13,5 @@
"scripts": {
"start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
},
"version": "0.0.4"
"version": "0.0.7"
}
@@ -1,5 +1,30 @@
# @llamaindex/autotool-02-next-example
## 0.1.51
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
- @llamaindex/autotool@2.0.1
## 0.1.50
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
- @llamaindex/autotool@2.0.1
## 0.1.49
### Patch Changes
- llamaindex@0.5.24
- @llamaindex/autotool@2.0.1
## 0.1.48
### Patch Changes
@@ -1,7 +1,7 @@
{
"name": "@llamaindex/autotool-02-next-example",
"private": true,
"version": "0.1.48",
"version": "0.1.51",
"scripts": {
"dev": "next dev",
"build": "next build",
+1 -1
View File
@@ -51,7 +51,7 @@
"unplugin": "^1.12.2"
},
"peerDependencies": {
"llamaindex": "^0.5.23",
"llamaindex": "^0.5.26",
"openai": "^4",
"typescript": "^4"
},
+12
View File
@@ -1,5 +1,17 @@
# @llamaindex/cloud
## 0.2.4
### Patch Changes
- 4810364: fix: bump version
## 0.2.3
### Patch Changes
- 0bf8d80: fix: bump version
## 0.2.2
### Patch Changes
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/cloud",
"version": "0.2.2",
"version": "0.2.4",
"type": "module",
"license": "MIT",
"scripts": {
+22
View File
@@ -1,5 +1,27 @@
# @llamaindex/experimental
## 0.0.76
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.0.75
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.0.74
### Patch Changes
- llamaindex@0.5.24
## 0.0.73
### Patch Changes
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@llamaindex/experimental",
"description": "Experimental package for LlamaIndexTS",
"version": "0.0.73",
"version": "0.0.76",
"type": "module",
"types": "dist/type/index.d.ts",
"main": "dist/cjs/index.js",
+26
View File
@@ -1,5 +1,31 @@
# llamaindex
## 0.5.26
### Patch Changes
- ffe0cd1: faet: add openai o1 support
- ffe0cd1: feat: add PostgreSQL storage
## 0.5.25
### Patch Changes
- 4810364: fix: handle `RouterQueryEngine` with string query
- d3bc663: refactor: export vector store only in nodejs environment on top level
If you see some missing modules error, please change vector store related imports to `llamaindex/vector-store`
- Updated dependencies [4810364]
- @llamaindex/cloud@0.2.4
## 0.5.24
### Patch Changes
- Updated dependencies [0bf8d80]
- @llamaindex/cloud@0.2.3
## 0.5.23
### Patch Changes
@@ -1,5 +1,27 @@
# @llamaindex/cloudflare-worker-agent-test
## 0.0.60
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.0.59
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.0.58
### Patch Changes
- llamaindex@0.5.24
## 0.0.57
### Patch Changes
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/cloudflare-worker-agent-test",
"version": "0.0.57",
"version": "0.0.60",
"type": "module",
"private": true,
"scripts": {
@@ -1,5 +1,27 @@
# @llamaindex/next-agent-test
## 0.1.60
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.1.59
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.1.58
### Patch Changes
- llamaindex@0.5.24
## 0.1.57
### Patch Changes
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/next-agent-test",
"version": "0.1.57",
"version": "0.1.60",
"private": true,
"scripts": {
"dev": "next dev",
@@ -1,5 +1,27 @@
# test-edge-runtime
## 0.1.59
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.1.58
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.1.57
### Patch Changes
- llamaindex@0.5.24
## 0.1.56
### Patch Changes
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/nextjs-edge-runtime-test",
"version": "0.1.56",
"version": "0.1.59",
"private": true,
"scripts": {
"dev": "next dev",
@@ -1,5 +1,27 @@
# @llamaindex/next-node-runtime
## 0.0.41
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.0.40
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.0.39
### Patch Changes
- llamaindex@0.5.24
## 0.0.38
### Patch Changes
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/next-node-runtime-test",
"version": "0.0.38",
"version": "0.0.41",
"private": true,
"scripts": {
"dev": "next dev",
@@ -1,5 +1,27 @@
# @llamaindex/waku-query-engine-test
## 0.0.60
### Patch Changes
- Updated dependencies [ffe0cd1]
- Updated dependencies [ffe0cd1]
- llamaindex@0.5.26
## 0.0.59
### Patch Changes
- Updated dependencies [4810364]
- Updated dependencies [d3bc663]
- llamaindex@0.5.25
## 0.0.58
### Patch Changes
- llamaindex@0.5.24
## 0.0.57
### Patch Changes
@@ -1,6 +1,6 @@
{
"name": "@llamaindex/waku-query-engine-test",
"version": "0.0.57",
"version": "0.0.60",
"type": "module",
"private": true,
"scripts": {
@@ -20,6 +20,7 @@
"@types/react-dom": "18.3.0",
"autoprefixer": "10.4.20",
"tailwindcss": "3.4.10",
"typescript": "5.5.4"
"typescript": "5.5.4",
"vite-plugin-wasm": "^3.3.0"
}
}
@@ -11,15 +11,22 @@ export default async function RootLayout({ children }: RootLayoutProps) {
const data = await getData();
return (
<div className="font-['Nunito']">
<meta property="description" content={data.description} />
<link rel="icon" type="image/png" href={data.icon} />
<Header />
<main className="m-6 flex items-center *:min-h-64 *:min-w-64 lg:m-0 lg:min-h-svh lg:justify-center">
{children}
</main>
<Footer />
</div>
<html>
<head>
<meta property="description" content={data.description} />
<link rel="icon" type="image/png" href={data.icon} />
<title>LlamaIndex Waku Example</title>
</head>
<body>
<div className="font-['Nunito']">
<Header />
<main className="m-6 flex items-center *:min-h-64 *:min-w-64 lg:m-0 lg:min-h-svh lg:justify-center">
{children}
</main>
<Footer />
</div>
</body>
</html>
);
}
@@ -31,7 +38,6 @@ const getData = async () => {
return data;
};
export const getConfig = async () => {
return {
render: "static",
@@ -0,0 +1,8 @@
import wasm from "vite-plugin-wasm";
export default {
plugins: [wasm()],
ssr: {
external: ["tiktoken"],
},
};
+67
View File
@@ -0,0 +1,67 @@
import { LLMSingleSelector, Settings } from "llamaindex";
import assert from "node:assert";
import { test } from "node:test";
import { mockLLMEvent } from "./utils.js";
await test("#1177", async (t) => {
await mockLLMEvent(t, "#1177");
await t.test(async () => {
const selector = new LLMSingleSelector({
llm: Settings.llm,
});
{
const result = await selector.select(
[
{
description: "Math calculation",
},
{
description: "Search from google",
},
],
"calculate 2 + 2",
);
assert.equal(result.selections.length, 1);
assert.equal(result.selections.at(0)!.index, 0);
}
{
const result = await selector.select(
[
{
description: "Math calculation",
},
{
description: "Search from google",
},
],
{
query: "calculate 2 + 2",
},
);
assert.equal(result.selections.length, 1);
assert.equal(result.selections.at(0)!.index, 0);
}
{
const result = await selector.select(
[
{
description: "Math calculation",
},
{
description: "Search from google",
},
],
{
query: [
{
type: "text",
text: "calculate 2 + 2",
},
],
},
);
assert.equal(result.selections.length, 1);
assert.equal(result.selections.at(0)!.index, 0);
}
});
});
@@ -0,0 +1,67 @@
{
"llmEventStart": [
{
"id": "PRESERVE_0",
"messages": [
{
"content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n {\n \"choice\": 1,\n \"reason\": \"<insert reason for choice>\"\n },\n ...\n]\n",
"role": "user"
}
]
},
{
"id": "PRESERVE_1",
"messages": [
{
"content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n {\n \"choice\": 1,\n \"reason\": \"<insert reason for choice>\"\n },\n ...\n]\n",
"role": "user"
}
]
},
{
"id": "PRESERVE_2",
"messages": [
{
"content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n {\n \"choice\": 1,\n \"reason\": \"<insert reason for choice>\"\n },\n ...\n]\n",
"role": "user"
}
]
}
],
"llmEventEnd": [
{
"id": "PRESERVE_0",
"response": {
"raw": null,
"message": {
"content": "[\n {\n \"choice\": 1,\n \"reason\": \"The question 'calculate 2 + 2' is directly asking for a math calculation, which corresponds to choice 1.\"\n }\n]",
"role": "assistant",
"options": {}
}
}
},
{
"id": "PRESERVE_1",
"response": {
"raw": null,
"message": {
"content": "[\n {\n \"choice\": 1,\n \"reason\": \"The question 'calculate 2 + 2' is asking for a mathematical calculation, which directly corresponds to choice 1: Math calculation.\"\n }\n]",
"role": "assistant",
"options": {}
}
}
},
{
"id": "PRESERVE_2",
"response": {
"raw": null,
"message": {
"content": "[\n {\n \"choice\": 1,\n \"reason\": \"The question 'calculate 2 + 2' is asking for a mathematical calculation, which directly corresponds to choice 1: Math calculation.\"\n }\n]",
"role": "assistant",
"options": {}
}
}
}
],
"llmEventStream": []
}
@@ -0,0 +1,90 @@
import { Document, VectorStoreQueryMode } from "llamaindex";
import { PGVectorStore } from "llamaindex/vector-store/PGVectorStore";
import assert from "node:assert";
import { test } from "node:test";
import pg from "pg";
import { registerTypes } from "pgvector/pg";
let pgClient: pg.Client | pg.Pool;
test.afterEach(async () => {
await pgClient.end();
});
await test("init with client", async () => {
pgClient = new pg.Client({
database: "llamaindex_node_test",
});
await pgClient.connect();
await pgClient.query("CREATE EXTENSION IF NOT EXISTS vector");
await registerTypes(pgClient);
const vectorStore = new PGVectorStore(pgClient);
assert.deepStrictEqual(await vectorStore.client(), pgClient);
});
await test("init with pool", async () => {
pgClient = new pg.Pool({
database: "llamaindex_node_test",
});
await pgClient.query("CREATE EXTENSION IF NOT EXISTS vector");
const client = await pgClient.connect();
await registerTypes(client);
const vectorStore = new PGVectorStore(client);
assert.deepStrictEqual(await vectorStore.client(), client);
client.release();
});
await test("init without client", async () => {
const vectorStore = new PGVectorStore({
database: "llamaindex_node_test",
});
pgClient = (await vectorStore.client()) as pg.Client;
assert.notDeepStrictEqual(pgClient, undefined);
});
await test("simple node", async () => {
const dimensions = 3;
const schemaName =
"llamaindex_vector_store_test_" + Math.random().toString(36).substring(7);
const nodeId = "5bb16627-f6c0-459c-bb18-71642813ef21";
const node = new Document({
text: "hello world",
id_: nodeId,
embedding: [0.1, 0.2, 0.3],
});
const vectorStore = new PGVectorStore({
database: "llamaindex_node_test",
dimensions,
schemaName,
});
await vectorStore.add([node]);
{
const result = await vectorStore.query({
mode: VectorStoreQueryMode.DEFAULT,
similarityTopK: 1,
queryEmbedding: [1, 2, 3],
});
const actualJSON = result.nodes![0]!.toJSON();
assert.deepStrictEqual(actualJSON, {
...node.toJSON(),
hash: actualJSON.hash,
metadata: actualJSON.metadata,
});
assert.deepStrictEqual(result.ids, [nodeId]);
assert.deepStrictEqual(result.similarities, [1]);
}
await vectorStore.delete(nodeId);
{
const result = await vectorStore.query({
mode: VectorStoreQueryMode.DEFAULT,
similarityTopK: 1,
queryEmbedding: [1, 2, 3],
});
assert.deepStrictEqual(result.nodes, []);
}
pgClient = (await vectorStore.client()) as pg.Client;
});
+13 -5
View File
@@ -1,6 +1,6 @@
{
"name": "llamaindex",
"version": "0.5.23",
"version": "0.5.26",
"license": "MIT",
"type": "module",
"keywords": [
@@ -56,11 +56,9 @@
"md-utils-ts": "^2.0.0",
"mongodb": "^6.7.0",
"notion-md-crawler": "^1.0.0",
"openai": "^4.57.0",
"openai": "^4.60.0",
"papaparse": "^5.4.1",
"pathe": "^1.1.2",
"pg": "^8.12.0",
"pgvector": "^0.2.0",
"portkey-ai": "0.1.16",
"rake-modified": "^1.0.8",
"string-strip-html": "^13.4.8",
@@ -72,11 +70,19 @@
"zod": "^3.23.8"
},
"peerDependencies": {
"@notionhq/client": "^2.2.15"
"@notionhq/client": "^2.2.15",
"pg": "^8.12.0",
"pgvector": "0.2.0"
},
"peerDependenciesMeta": {
"@notionhq/client": {
"optional": true
},
"pg": {
"optional": true
},
"pgvector": {
"optional": true
}
},
"devDependencies": {
@@ -85,6 +91,8 @@
"@swc/core": "^1.7.22",
"concurrently": "^8.2.2",
"glob": "^11.0.0",
"pg": "^8.12.0",
"pgvector": "0.2.0",
"typescript": "^5.5.4"
},
"engines": {
+4 -2
View File
@@ -59,10 +59,12 @@ class GlobalSettings implements Config {
}
get llm(): LLM {
if (CoreSettings.llm === null) {
// fixme: we might need check internal error instead of try-catch here
try {
CoreSettings.llm;
} catch (error) {
CoreSettings.llm = new OpenAI();
}
return CoreSettings.llm;
}
+4
View File
@@ -17,3 +17,7 @@ export { GeminiVertexSession } from "./llm/gemini/vertex.js";
// Expose AzureDynamicSessionTool for node.js runtime only
export { JinaAIEmbedding } from "./embeddings/JinaAIEmbedding.js";
export { AzureDynamicSessionTool } from "./tools/AzureDynamicSessionTool.node.js";
// Don't export vector store modules for non-node.js runtime on top level,
// as we cannot guarantee that they will work in other environments
export * from "./vector-store.js";
@@ -29,16 +29,16 @@ import {
import type { BaseNodePostprocessor } from "../../postprocessors/types.js";
import type { StorageContext } from "../../storage/StorageContext.js";
import { storageContextFromDefaults } from "../../storage/StorageContext.js";
import type { BaseIndexStore } from "../../storage/indexStore/types.js";
import type { BaseSynthesizer } from "../../synthesizers/types.js";
import type { QueryEngine } from "../../types.js";
import type {
MetadataFilters,
VectorStore,
VectorStoreByType,
VectorStoreQueryResult,
} from "../../storage/index.js";
import type { BaseIndexStore } from "../../storage/indexStore/types.js";
import { VectorStoreQueryMode } from "../../storage/vectorStore/types.js";
import type { BaseSynthesizer } from "../../synthesizers/types.js";
import type { QueryEngine } from "../../types.js";
} from "../../vector-store/index.js";
import { VectorStoreQueryMode } from "../../vector-store/types.js";
import type { BaseIndexInit } from "../BaseIndex.js";
import { BaseIndex } from "../BaseIndex.js";
import { IndexDict, IndexStructType } from "../json-to-index-struct.js";
@@ -7,10 +7,7 @@ import {
type Metadata,
} from "@llamaindex/core/schema";
import type { BaseDocumentStore } from "../storage/docStore/types.js";
import type {
VectorStore,
VectorStoreByType,
} from "../storage/vectorStore/types.js";
import type { VectorStore, VectorStoreByType } from "../vector-store/types.js";
import { IngestionCache, getTransformationHash } from "./IngestionCache.js";
import {
DocStoreStrategy,
@@ -1,6 +1,6 @@
import { BaseNode, TransformComponent } from "@llamaindex/core/schema";
import type { BaseDocumentStore } from "../../storage/docStore/types.js";
import type { VectorStore } from "../../storage/vectorStore/types.js";
import type { VectorStore } from "../../vector-store/types.js";
import { classify } from "./classify.js";
/**
@@ -1,6 +1,6 @@
import { BaseNode, TransformComponent } from "@llamaindex/core/schema";
import type { BaseDocumentStore } from "../../storage/docStore/types.js";
import type { VectorStore } from "../../storage/vectorStore/types.js";
import type { VectorStore } from "../../vector-store/types.js";
import { classify } from "./classify.js";
/**
@@ -1,6 +1,6 @@
import { TransformComponent } from "@llamaindex/core/schema";
import type { BaseDocumentStore } from "../../storage/docStore/types.js";
import type { VectorStore } from "../../storage/vectorStore/types.js";
import type { VectorStore } from "../../vector-store/types.js";
import { DuplicatesStrategy } from "./DuplicatesStrategy.js";
import { UpsertsAndDeleteStrategy } from "./UpsertsAndDeleteStrategy.js";
import { UpsertsStrategy } from "./UpsertsStrategy.js";
+21 -1
View File
@@ -97,6 +97,9 @@ export function getOpenAISession(
}
export const GPT4_MODELS = {
"chatgpt-4o-latest": {
contextWindow: 128000,
},
"gpt-4": { contextWindow: 8192 },
"gpt-4-32k": { contextWindow: 32768 },
"gpt-4-32k-0613": { contextWindow: 32768 },
@@ -129,12 +132,28 @@ export const GPT35_MODELS = {
"gpt-3.5-turbo-0301": { contextWindow: 16385 },
};
export const O1_MODELS = {
"o1-preview": {
contextWindow: 128000,
},
"o1-preview-2024-09-12": {
contextWindow: 128000,
},
"o1-mini": {
contextWindow: 128000,
},
"o1-mini-2024-09-12": {
contextWindow: 128000,
},
};
/**
* We currently support GPT-3.5 and GPT-4 models
*/
export const ALL_AVAILABLE_OPENAI_MODELS = {
...GPT4_MODELS,
...GPT35_MODELS,
...O1_MODELS,
} satisfies Record<ChatModel, { contextWindow: number }>;
export function isFunctionCallingModel(llm: LLM): llm is OpenAI {
@@ -148,7 +167,8 @@ export function isFunctionCallingModel(llm: LLM): llm is OpenAI {
}
const isChatModel = Object.keys(ALL_AVAILABLE_OPENAI_MODELS).includes(model);
const isOld = model.includes("0314") || model.includes("0301");
return isChatModel && !isOld;
const isO1 = model.startsWith("o1");
return isChatModel && !isOld && !isO1;
}
export type OpenAIAdditionalMetadata = {};
@@ -12,8 +12,8 @@ const formatStr = `The output should be ONLY JSON formatted as a JSON instance.
Here is an example:
[
{
choice: 1,
reason: "<insert reason for choice>"
"choice": 1,
"reason": "<insert reason for choice>"
},
...
]
@@ -159,7 +159,7 @@ export class LLMSingleSelector extends BaseSelector {
const prompt = this.prompt.format({
numChoices: `${choicesText.length}`,
context: choicesText,
query: extractText(query.query),
query: extractText(query),
});
const formattedPrompt = this.outputParser.format(prompt);
@@ -5,12 +5,12 @@ import {
import { ModalityType, ObjectType } from "@llamaindex/core/schema";
import { path } from "@llamaindex/env";
import { getImageEmbedModel } from "../internal/settings/image-embed-model.js";
import { SimpleVectorStore } from "../vector-store/SimpleVectorStore.js";
import type { VectorStore, VectorStoreByType } from "../vector-store/types.js";
import { SimpleDocumentStore } from "./docStore/SimpleDocumentStore.js";
import type { BaseDocumentStore } from "./docStore/types.js";
import { SimpleIndexStore } from "./indexStore/SimpleIndexStore.js";
import type { BaseIndexStore } from "./indexStore/types.js";
import { SimpleVectorStore } from "./vectorStore/SimpleVectorStore.js";
import type { VectorStore, VectorStoreByType } from "./vectorStore/types.js";
export interface StorageContext {
docStore: BaseDocumentStore;
@@ -0,0 +1,21 @@
import { DEFAULT_NAMESPACE } from "@llamaindex/core/global";
import { PostgresKVStore } from "../kvStore/PostgresKVStore.js";
import { KVDocumentStore } from "./KVDocumentStore.js";
const DEFAULT_TABLE_NAME = "llamaindex_doc_store";
export class PostgresDocumentStore extends KVDocumentStore {
constructor(config?: {
schemaName?: string;
tableName?: string;
connectionString?: string;
namespace?: string;
}) {
const kvStore = new PostgresKVStore({
schemaName: config?.schemaName,
tableName: config?.tableName || DEFAULT_TABLE_NAME,
});
const namespace = config?.namespace || DEFAULT_NAMESPACE;
super(kvStore, namespace);
}
}
+3 -10
View File
@@ -1,20 +1,13 @@
export { SimpleChatStore } from "./chatStore/SimpleChatStore.js";
export * from "./chatStore/types.js";
export { PostgresDocumentStore } from "./docStore/PostgresDocumentStore.js";
export { SimpleDocumentStore } from "./docStore/SimpleDocumentStore.js";
export * from "./docStore/types.js";
export * from "./FileSystem.js";
export { PostgresIndexStore } from "./indexStore/PostgresIndexStore.js";
export { SimpleIndexStore } from "./indexStore/SimpleIndexStore.js";
export * from "./indexStore/types.js";
export { PostgresKVStore } from "./kvStore/PostgresKVStore.js";
export { SimpleKVStore } from "./kvStore/SimpleKVStore.js";
export * from "./kvStore/types.js";
export * from "./StorageContext.js";
export { AstraDBVectorStore } from "./vectorStore/AstraDBVectorStore.js";
export { ChromaVectorStore } from "./vectorStore/ChromaVectorStore.js";
export { MilvusVectorStore } from "./vectorStore/MilvusVectorStore.js";
export { MongoDBAtlasVectorSearch } from "./vectorStore/MongoDBAtlasVectorStore.js";
export { PGVectorStore } from "./vectorStore/PGVectorStore.js";
export { PineconeVectorStore } from "./vectorStore/PineconeVectorStore.js";
export { QdrantVectorStore } from "./vectorStore/QdrantVectorStore.js";
export { SimpleVectorStore } from "./vectorStore/SimpleVectorStore.js";
export * from "./vectorStore/types.js";
export { WeaviateVectorStore } from "./vectorStore/WeaviateVectorStore.js";
@@ -0,0 +1,21 @@
import { DEFAULT_NAMESPACE } from "@llamaindex/core/global";
import { PostgresKVStore } from "../kvStore/PostgresKVStore.js";
import { KVIndexStore } from "./KVIndexStore.js";
const DEFAULT_TABLE_NAME = "llamaindex_index_store";
export class PostgresIndexStore extends KVIndexStore {
constructor(config?: {
schemaName?: string;
tableName?: string;
connectionString?: string;
namespace?: string;
}) {
const kvStore = new PostgresKVStore({
schemaName: config?.schemaName,
tableName: config?.tableName || DEFAULT_TABLE_NAME,
});
const namespace = config?.namespace || DEFAULT_NAMESPACE;
super(kvStore, namespace);
}
}
@@ -0,0 +1,140 @@
import { DEFAULT_COLLECTION } from "@llamaindex/core/global";
import type pg from "pg";
import { BaseKVStore } from "./types.js";
export type DataType = Record<string, Record<string, any>>;
const DEFAULT_SCHEMA_NAME = "public";
const DEFAULT_TABLE_NAME = "llamaindex_kv_store";
export class PostgresKVStore extends BaseKVStore {
private schemaName: string;
private tableName: string;
private connectionString: string | undefined = undefined;
private db?: pg.Client;
constructor(config?: {
schemaName?: string | undefined;
tableName?: string | undefined;
connectionString?: string | undefined;
}) {
super();
this.schemaName = config?.schemaName || DEFAULT_SCHEMA_NAME;
this.tableName = config?.tableName || DEFAULT_TABLE_NAME;
this.connectionString = config?.connectionString;
}
private async getDb(): Promise<pg.Client> {
if (!this.db) {
try {
const pg = await import("pg");
const { Client } = pg.default ? pg.default : pg;
const db = new Client({ connectionString: this.connectionString });
await db.connect();
await this.checkSchema(db);
this.db = db;
} catch (err) {
console.error(err);
return Promise.reject(err instanceof Error ? err : new Error(`${err}`));
}
}
return Promise.resolve(this.db);
}
private async checkSchema(db: pg.Client) {
await db.query(`CREATE SCHEMA IF NOT EXISTS ${this.schemaName}`);
const tbl = `CREATE TABLE IF NOT EXISTS ${this.schemaName}.${this.tableName} (
id uuid DEFAULT gen_random_uuid() PRIMARY KEY,
collection VARCHAR,
key VARCHAR,
value JSONB DEFAULT '{}'
)`;
await db.query(tbl);
const idxs = `CREATE INDEX IF NOT EXISTS idx_${this.tableName}_collection ON ${this.schemaName}.${this.tableName} (collection);
CREATE INDEX IF NOT EXISTS idx_${this.tableName}_key ON ${this.schemaName}.${this.tableName} (key);`;
await db.query(idxs);
return db;
}
client() {
return this.getDb();
}
async put(
key: string,
val: any,
collection: string = DEFAULT_COLLECTION,
): Promise<void> {
const db = await this.getDb();
try {
await db.query("BEGIN");
const sql = `
INSERT INTO ${this.schemaName}.${this.tableName}
(collection, key, value)
VALUES ($1, $2, $3)
ON CONFLICT (id) DO UPDATE SET
collection = EXCLUDED.collection,
key = EXCLUDED.key,
value = EXCLUDED.value
RETURNING id
`;
const values = [collection, key, val];
await db.query(sql, values);
await db.query("COMMIT");
} catch (error) {
await db.query("ROLLBACK");
throw error;
}
}
async get(
key: string,
collection: string = DEFAULT_COLLECTION,
): Promise<any> {
const db = await this.getDb();
try {
await db.query("BEGIN");
const sql = `SELECT * FROM ${this.schemaName}.${this.tableName} WHERE key = $1 AND collection = $2`;
const result = await db.query(sql, [key, collection]);
await db.query("COMMIT");
return result.rows[0].value;
} catch (error) {
await db.query("ROLLBACK");
throw error;
}
}
async getAll(collection: string = DEFAULT_COLLECTION): Promise<DataType> {
const db = await this.getDb();
try {
await db.query("BEGIN");
const sql = `SELECT * FROM ${this.schemaName}.${this.tableName} WHERE collection = $1`;
const result = await db.query(sql, [collection]);
await db.query("COMMIT");
return result.rows.reduce((acc, row) => {
acc[row.key] = row.value;
return acc;
}, {});
} catch (error) {
await db.query("ROLLBACK");
throw error;
}
}
async delete(
key: string,
collection: string = DEFAULT_COLLECTION,
): Promise<boolean> {
const db = await this.getDb();
try {
await db.query("BEGIN");
const sql = `DELETE FROM ${this.schemaName}.${this.tableName} WHERE key = $1 AND collection = $2`;
const result = await db.query(sql, [key, collection]);
await db.query("COMMIT");
return !!result.rowCount && result.rowCount > 0;
} catch (error) {
await db.query("ROLLBACK");
throw error;
}
}
}
+1
View File
@@ -0,0 +1 @@
export * from "./vector-store/index.js";
@@ -3,10 +3,9 @@ import type pg from "pg";
import {
FilterCondition,
FilterOperator,
VectorStoreBase,
type IEmbedModel,
type MetadataFilter,
type MetadataFilterValue,
VectorStoreBase,
type VectorStoreNoEmbedModel,
type VectorStoreQuery,
type VectorStoreQueryResult,
@@ -14,12 +13,22 @@ import {
import { escapeLikeString } from "./utils.js";
import type { BaseEmbedding } from "@llamaindex/core/embeddings";
import type { BaseNode, Metadata } from "@llamaindex/core/schema";
import { Document, MetadataMode } from "@llamaindex/core/schema";
export const PGVECTOR_SCHEMA = "public";
export const PGVECTOR_TABLE = "llamaindex_embedding";
export type PGVectorStoreConfig = {
schemaName?: string | undefined;
tableName?: string | undefined;
database?: string | undefined;
connectionString?: string | undefined;
dimensions?: number | undefined;
embedModel?: BaseEmbedding | undefined;
};
/**
* Provides support for writing and querying vector data in Postgres.
* Note: Can't be used with data created using the Python version of the vector store (https://docs.llamaindex.ai/en/stable/examples/vector_stores/postgres.html)
@@ -33,10 +42,12 @@ export class PGVectorStore
private collection: string = "";
private schemaName: string = PGVECTOR_SCHEMA;
private tableName: string = PGVECTOR_TABLE;
private database: string | undefined = undefined;
private connectionString: string | undefined = undefined;
private dimensions: number = 1536;
private db?: pg.Client;
private db?: pg.ClientBase;
/**
* Constructs a new instance of the PGVectorStore
@@ -48,26 +59,27 @@ export class PGVectorStore
* PGPASSWORD=your database password
* PGDATABASE=your database name
* PGPORT=your database port
*
* @param {object} config - The configuration settings for the instance.
* @param {string} config.schemaName - The name of the schema (optional). Defaults to PGVECTOR_SCHEMA.
* @param {string} config.tableName - The name of the table (optional). Defaults to PGVECTOR_TABLE.
* @param {string} config.connectionString - The connection string (optional).
* @param {number} config.dimensions - The dimensions of the embedding model.
*/
constructor(
config?: {
schemaName?: string;
tableName?: string;
connectionString?: string;
dimensions?: number;
} & Partial<IEmbedModel>,
) {
super(config?.embedModel);
this.schemaName = config?.schemaName ?? PGVECTOR_SCHEMA;
this.tableName = config?.tableName ?? PGVECTOR_TABLE;
this.connectionString = config?.connectionString;
this.dimensions = config?.dimensions ?? 1536;
constructor(configOrClient?: PGVectorStoreConfig | pg.ClientBase) {
// We cannot import pg from top level, it might have side effects
// so we only check if the config.connect function exists
if (
configOrClient &&
"connect" in configOrClient &&
typeof configOrClient.connect === "function"
) {
const db = configOrClient as pg.ClientBase;
super();
this.db = db;
} else {
const config = configOrClient as PGVectorStoreConfig;
super(config?.embedModel);
this.schemaName = config?.schemaName ?? PGVECTOR_SCHEMA;
this.tableName = config?.tableName ?? PGVECTOR_TABLE;
this.database = config?.database;
this.connectionString = config?.connectionString;
this.dimensions = config?.dimensions ?? 1536;
}
}
/**
@@ -92,7 +104,7 @@ export class PGVectorStore
return this.collection;
}
private async getDb(): Promise<pg.Client> {
private async getDb(): Promise<pg.ClientBase> {
if (!this.db) {
try {
const pg = await import("pg");
@@ -102,6 +114,7 @@ export class PGVectorStore
// Create DB connection
// Read connection params from env - see comment block above
const db = new Client({
database: this.database,
connectionString: this.connectionString,
});
await db.connect();
@@ -110,9 +123,6 @@ export class PGVectorStore
await db.query("CREATE EXTENSION IF NOT EXISTS vector");
await registerType(db);
// Check schema, table(s), index(es)
await this.checkSchema(db);
// All good? Keep the connection reference
this.db = db;
} catch (err) {
@@ -121,10 +131,15 @@ export class PGVectorStore
}
}
const db = this.db;
// Check schema, table(s), index(es)
await this.checkSchema(db);
return Promise.resolve(this.db);
}
private async checkSchema(db: pg.Client) {
private async checkSchema(db: pg.ClientBase) {
await db.query(`CREATE SCHEMA IF NOT EXISTS ${this.schemaName}`);
const tbl = `CREATE TABLE IF NOT EXISTS ${this.schemaName}.${this.tableName}(
@@ -171,26 +186,22 @@ export class PGVectorStore
}
private getDataToInsert(embeddingResults: BaseNode<Metadata>[]) {
const result = [];
for (let index = 0; index < embeddingResults.length; index++) {
const row = embeddingResults[index]!;
return embeddingResults.map((node) => {
const id: any = node.id_.length ? node.id_ : null;
const meta = node.metadata || {};
if (!meta.create_date) {
meta.create_date = new Date();
}
const id: any = row.id_.length ? row.id_ : null;
const meta = row.metadata || {};
meta.create_date = new Date();
const params = [
return [
id,
"",
this.collection,
row.getContent(MetadataMode.EMBED),
node.getContent(MetadataMode.NONE),
meta,
"[" + row.getEmbedding().join(",") + "]",
"[" + node.getEmbedding().join(",") + "]",
];
result.push(params);
}
return result;
});
}
/**
@@ -201,7 +212,7 @@ export class PGVectorStore
*/
async add(embeddingResults: BaseNode<Metadata>[]): Promise<string[]> {
if (embeddingResults.length === 0) {
console.debug("Empty list sent to PGVectorStore::add");
console.warn("Empty list sent to PGVectorStore::add");
return [];
}
@@ -2,11 +2,8 @@ import type { BaseEmbedding } from "@llamaindex/core/embeddings";
import { DEFAULT_PERSIST_DIR } from "@llamaindex/core/global";
import type { BaseNode } from "@llamaindex/core/schema";
import { fs, path } from "@llamaindex/env";
import {
getTopKEmbeddings,
getTopKMMREmbeddings,
} from "../../internal/utils.js";
import { exists } from "../FileSystem.js";
import { getTopKEmbeddings, getTopKMMREmbeddings } from "../internal/utils.js";
import { exists } from "../storage/FileSystem.js";
import {
FilterOperator,
VectorStoreBase,
@@ -0,0 +1,10 @@
export * from "./AstraDBVectorStore.js";
export * from "./ChromaVectorStore.js";
export * from "./MilvusVectorStore.js";
export * from "./MongoDBAtlasVectorStore.js";
export * from "./PGVectorStore.js";
export * from "./PineconeVectorStore.js";
export * from "./QdrantVectorStore.js";
export * from "./SimpleVectorStore.js";
export * from "./types.js";
export * from "./WeaviateVectorStore.js";
@@ -1,6 +1,6 @@
import type { BaseEmbedding } from "@llamaindex/core/embeddings";
import type { BaseNode, ModalityType } from "@llamaindex/core/schema";
import { getEmbeddedModel } from "../../internal/settings/EmbedModel.js";
import { getEmbeddedModel } from "../internal/settings/EmbedModel.js";
export interface VectorStoreQueryResult {
nodes?: BaseNode[];
@@ -2,7 +2,7 @@ import { Document, MetadataMode } from "@llamaindex/core/schema";
import {
metadataDictToNode,
nodeToMetadata,
} from "llamaindex/storage/vectorStore/utils";
} from "llamaindex/vector-store/utils";
import { beforeEach, describe, expect, test } from "vitest";
describe("Testing VectorStore utils", () => {
@@ -1,5 +1,5 @@
import type { BaseNode } from "@llamaindex/core/schema";
import { QdrantVectorStore } from "llamaindex/storage/index";
import { QdrantVectorStore } from "llamaindex/vector-store";
export class TestableQdrantVectorStore extends QdrantVectorStore {
public nodes: BaseNode[] = [];
@@ -4,7 +4,7 @@ import type { Mocked } from "vitest";
import { beforeEach, describe, expect, it, vi } from "vitest";
import { QdrantClient } from "@qdrant/js-client-rest";
import { VectorStoreQueryMode } from "llamaindex/storage/index";
import { VectorStoreQueryMode } from "llamaindex/vector-store";
import { TestableQdrantVectorStore } from "../mocks/TestableQdrantVectorStore.js";
vi.mock("@qdrant/js-client-rest");
+55 -18
View File
@@ -152,7 +152,7 @@ importers:
version: 2.4.6
chromadb:
specifier: ^1.8.1
version: 1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.57.0(encoding@0.1.13)(zod@3.23.8))
version: 1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.60.0(encoding@0.1.13)(zod@3.23.8))
commander:
specifier: ^12.1.0
version: 12.1.0
@@ -276,7 +276,7 @@ importers:
version: 1.1.0(@types/react@18.3.5)(react@18.3.1)
ai:
specifier: ^3.3.21
version: 3.3.21(openai@4.57.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8)
version: 3.3.21(openai@4.60.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8)
class-variance-authority:
specifier: ^0.7.0
version: 0.7.0
@@ -554,7 +554,7 @@ importers:
version: 4.7.0
chromadb:
specifier: 1.8.1
version: 1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.57.0(encoding@0.1.13)(zod@3.23.8))
version: 1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.60.0(encoding@0.1.13)(zod@3.23.8))
cohere-ai:
specifier: 7.13.0
version: 7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13)
@@ -586,20 +586,14 @@ importers:
specifier: ^1.0.0
version: 1.0.0(encoding@0.1.13)
openai:
specifier: ^4.57.0
version: 4.57.0(encoding@0.1.13)(zod@3.23.8)
specifier: ^4.60.0
version: 4.60.0(encoding@0.1.13)(zod@3.23.8)
papaparse:
specifier: ^5.4.1
version: 5.4.1
pathe:
specifier: ^1.1.2
version: 1.1.2
pg:
specifier: ^8.12.0
version: 8.12.0
pgvector:
specifier: ^0.2.0
version: 0.2.0
portkey-ai:
specifier: 0.1.16
version: 0.1.16
@@ -643,6 +637,12 @@ importers:
glob:
specifier: ^11.0.0
version: 11.0.0
pg:
specifier: ^8.12.0
version: 8.12.0
pgvector:
specifier: 0.2.0
version: 0.2.0
typescript:
specifier: ^5.5.4
version: 5.5.4
@@ -700,7 +700,7 @@ importers:
dependencies:
ai:
specifier: ^3.3.21
version: 3.3.21(openai@4.57.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8)
version: 3.3.21(openai@4.60.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8)
llamaindex:
specifier: workspace:*
version: link:../../..
@@ -840,6 +840,9 @@ importers:
typescript:
specifier: 5.5.4
version: 5.5.4
vite-plugin-wasm:
specifier: ^3.3.0
version: 3.3.0(vite@5.4.2(@types/node@22.5.1)(terser@5.31.6))
packages/llamaindex/tests:
devDependencies:
@@ -8385,6 +8388,15 @@ packages:
zod:
optional: true
openai@4.60.0:
resolution: {integrity: sha512-U/wNmrUPdfsvU1GrKRP5mY5YHR3ev6vtdfNID6Sauz+oquWD8r+cXPL1xiUlYniosPKajy33muVHhGS/9/t6KA==}
hasBin: true
peerDependencies:
zod: ^3.23.8
peerDependenciesMeta:
zod:
optional: true
opener@1.5.2:
resolution: {integrity: sha512-ur5UIdyw5Y7yEj9wLzhqXiy6GZ3Mwx0yGI+5sMn2r0N0v3cKJvUmFH5yPP+WXh9e0xfyzyJX95D8l088DNFj7A==}
hasBin: true
@@ -10689,6 +10701,11 @@ packages:
engines: {node: ^18.0.0 || >=20.0.0}
hasBin: true
vite-plugin-wasm@3.3.0:
resolution: {integrity: sha512-tVhz6w+W9MVsOCHzxo6SSMSswCeIw4HTrXEi6qL3IRzATl83jl09JVO1djBqPSwfjgnpVHNLYcaMbaDX5WB/pg==}
peerDependencies:
vite: ^2 || ^3 || ^4 || ^5
vite@5.4.2:
resolution: {integrity: sha512-dDrQTRHp5C1fTFzcSaMxjk6vdpKvT+2/mIdE07Gw2ykehT49O0z/VHS3zZ8iV/Gh8BJJKHWOe5RjaNrW5xf/GA==}
engines: {node: ^18.0.0 || >=20.0.0}
@@ -15958,7 +15975,7 @@ snapshots:
clean-stack: 2.2.0
indent-string: 4.0.0
ai@3.3.21(openai@4.57.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8):
ai@3.3.21(openai@4.60.0(zod@3.23.8))(react@18.3.1)(sswr@2.1.0(svelte@4.2.19))(svelte@4.2.19)(vue@3.4.38(typescript@5.5.4))(zod@3.23.8):
dependencies:
'@ai-sdk/provider': 0.0.22
'@ai-sdk/provider-utils': 1.0.17(zod@3.23.8)
@@ -15975,7 +15992,7 @@ snapshots:
secure-json-parse: 2.7.0
zod-to-json-schema: 3.23.2(zod@3.23.8)
optionalDependencies:
openai: 4.57.0(zod@3.23.8)
openai: 4.60.0(zod@3.23.8)
react: 18.3.1
sswr: 2.1.0(svelte@4.2.19)
svelte: 4.2.19
@@ -16652,14 +16669,14 @@ snapshots:
chownr@2.0.0: {}
chromadb@1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.57.0(encoding@0.1.13)(zod@3.23.8)):
chromadb@1.8.1(@google/generative-ai@0.12.0)(cohere-ai@7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13))(encoding@0.1.13)(openai@4.60.0(encoding@0.1.13)(zod@3.23.8)):
dependencies:
cliui: 8.0.1
isomorphic-fetch: 3.0.0(encoding@0.1.13)
optionalDependencies:
'@google/generative-ai': 0.12.0
cohere-ai: 7.13.0(@aws-sdk/client-sso-oidc@3.637.0(@aws-sdk/client-sts@3.637.0))(encoding@0.1.13)
openai: 4.57.0(encoding@0.1.13)(zod@3.23.8)
openai: 4.60.0(encoding@0.1.13)(zod@3.23.8)
transitivePeerDependencies:
- encoding
@@ -20925,7 +20942,23 @@ snapshots:
transitivePeerDependencies:
- encoding
openai@4.57.0(zod@3.23.8):
openai@4.60.0(encoding@0.1.13)(zod@3.23.8):
dependencies:
'@types/node': 18.19.47
'@types/node-fetch': 2.6.11
'@types/qs': 6.9.15
abort-controller: 3.0.0
agentkeepalive: 4.5.0
form-data-encoder: 1.7.2
formdata-node: 4.4.1
node-fetch: 2.7.0(encoding@0.1.13)
qs: 6.13.0
optionalDependencies:
zod: 3.23.8
transitivePeerDependencies:
- encoding
openai@4.60.0(zod@3.23.8):
dependencies:
'@types/node': 18.19.47
'@types/node-fetch': 2.6.11
@@ -23350,7 +23383,7 @@ snapshots:
union@0.5.0:
dependencies:
qs: 6.11.2
qs: 6.13.0
unique-string@3.0.0:
dependencies:
@@ -23532,6 +23565,10 @@ snapshots:
- supports-color
- terser
vite-plugin-wasm@3.3.0(vite@5.4.2(@types/node@22.5.1)(terser@5.31.6)):
dependencies:
vite: 5.4.2(@types/node@22.5.1)(terser@5.31.6)
vite@5.4.2(@types/node@22.5.1)(terser@5.31.6):
dependencies:
esbuild: 0.21.5