Release 0.12.1 (#2239)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>

docs/src/content/docs/framework/modules/models/embeddings/ovhcloud.mdx

@@ -0,0 +1,123 @@
+---
+title: OVHcloud AI Endpoints
+---
+
+OVHcloud AI Endpoints provide OpenAI-compatible embedding models. The service can be used for free with rate limits, or with an API key for higher limits.
+
+OVHcloud is a global player and the leading European cloud provider operating over 450,000 servers within 40 data centers across 4 continents to reach 1.6 million customers in over 140 countries. Our product AI Endpoints offers access to various models with sovereignty, data privacy and GDPR compliance.
+
+You can find the full list of models in the [OVHcloud AI Endpoints catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/).
+
+## Installation
+
+```package-install
+npm i llamaindex @llamaindex/ovhcloud
+```
+
+## Authentication
+
+OVHcloud AI Endpoints can be used in two ways:
+
+1. **Free tier (with rate limits)**: No API key required. You can omit the `apiKey` parameter or set it to an empty string.
+2. **With API key**: For higher rate limits, generate an API key from the [OVHcloud Manager](https://ovh.com/manager) → Public Cloud → AI & Machine Learning → AI Endpoints → API keys.
+
+## Basic Usage
+
+```ts
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
+
+// Update Embed Model (using free tier)
+Settings.embedModel = new OVHcloudEmbedding();
+
+// Or with API key from environment variable
+import { config } from "dotenv";
+config();
+Settings.embedModel = new OVHcloudEmbedding({
+  apiKey: process.env.OVHCLOUD_API_KEY || "",
+});
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+By default, `OVHcloudEmbedding` uses the `BGE-M3` model. You can change the model by passing the model parameter to the constructor:
+
+```ts
+import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
+
+const model = "text-embedding-3-small";
+Settings.embedModel = new OVHcloudEmbedding({
+  model,
+});
+```
+
+You can also set the `maxRetries` and `timeout` parameters when initializing `OVHcloudEmbedding` for better control over the request behavior:
+
+```ts
+import { Settings } from "llamaindex";
+import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
+
+const model = "text-embedding-3-small";
+const maxRetries = 5;
+const timeout = 5000; // 5 seconds
+
+Settings.embedModel = new OVHcloudEmbedding({
+  model,
+  maxRetries,
+  timeout,
+});
+```
+
+## Standalone Usage
+
+```ts
+import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
+import { config } from "dotenv";
+// For standalone usage, you can optionally configure OVHCLOUD_API_KEY in .env file
+config();
+
+const main = async () => {
+  const model = "BGE-M3";
+  // Using without API key (free tier)
+  const embeddings = new OVHcloudEmbedding({ model });
+  const text = "What is the meaning of life?";
+  const response = await embeddings.embed([text]);
+  console.log(response);
+};
+
+main();
+```
+
+## Base URL
+
+The default base URL is `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`. You can override it if needed:
+
+```ts
+const embedding = new OVHcloudEmbedding({
+  model: "BGE-M3",
+  additionalSessionOptions: {
+    baseURL: "https://custom.endpoint.com/v1",
+  },
+});
+```
+
+## Resources
+
+- [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/)
+- [OVHcloud Manager](https://ovh.com/manager)
+- [OVHcloud AI Endpoints Documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/)
+
+## API Reference
+
+- [OVHcloudEmbedding](/typescript/framework-api-reference/classes/ovhcloudembedding/)
+

docs/src/content/docs/framework/modules/models/llms/ovhcloud.mdx

@@ -0,0 +1,164 @@
+---
+title: OVHcloud AI Endpoints
+---
+
+OVHcloud AI Endpoints provide serverless access to a variety of pre-trained AI models. The service is OpenAI-compatible and can be used for free with rate limits, or with an API key for higher limits.
+
+OVHcloud is a global player and the leading European cloud provider operating over 450,000 servers within 40 data centers across 4 continents to reach 1.6 million customers in over 140 countries. Our product AI Endpoints offers access to various models with sovereignty, data privacy and GDPR compliance.
+
+You can find the full list of models in the [OVHcloud AI Endpoints catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/).
+
+## Installation
+
+```package-install
+npm i llamaindex @llamaindex/ovhcloud
+```
+
+## Authentication
+
+OVHcloud AI Endpoints can be used in two ways:
+
+1. **Free tier (with rate limits)**: No API key required. You can omit the `apiKey` parameter or set it to an empty string.
+2. **With API key**: For higher rate limits, generate an API key from the [OVHcloud Manager](https://ovh.com/manager) → Public Cloud → AI & Machine Learning → AI Endpoints → API keys.
+
+## Basic Usage
+
+```ts
+import { OVHcloudLLM } from "@llamaindex/ovhcloud";
+import { Settings } from "llamaindex";
+
+// Using without API key (free tier with rate limits)
+Settings.llm = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+});
+
+// Or with API key from environment variable
+import { config } from "dotenv";
+config();
+Settings.llm = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+  apiKey: process.env.OVHCLOUD_API_KEY || "",
+});
+
+// Or with explicit API key
+Settings.llm = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+  apiKey: "YOUR_API_KEY",
+});
+```
+
+You can set the API key via environment variable:
+
+```bash
+export OVHCLOUD_API_KEY="<YOUR_API_KEY>"
+```
+
+## Load and index documents
+
+For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
+
+```ts
+import { Document, VectorStoreIndex } from "llamaindex";
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import { OVHcloudLLM } from "@llamaindex/ovhcloud";
+import { Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use custom LLM
+const model = "gpt-oss-120b";
+Settings.llm = new OVHcloudLLM({ model, temperature: 0 });
+
+async function main() {
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const query = "What is the meaning of life?";
+
+  // Query
+  const response = await queryEngine.query({
+    query,
+  });
+
+  // Log the response
+  console.log(response.response);
+}
+```
+
+## Streaming
+
+OVHcloud AI Endpoints supports streaming responses:
+
+```ts
+import { OVHcloudLLM } from "@llamaindex/ovhcloud";
+
+const llm = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+});
+
+const generator = await llm.chat({
+  messages: [
+    {
+      role: "user",
+      content: "Tell me about OVHcloud AI Endpoints",
+    },
+  ],
+  stream: true,
+});
+
+for await (const message of generator) {
+  process.stdout.write(message.delta);
+}
+```
+
+## Base URL
+
+The default base URL is `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`. You can override it if needed:
+
+```ts
+const llm = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+  additionalSessionOptions: {
+    baseURL: "https://custom.endpoint.com/v1",
+  },
+});
+```
+
+## Resources
+
+- [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/)
+- [OVHcloud Manager](https://ovh.com/manager)
+- [OVHcloud AI Endpoints Documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/)
+
+## API Reference
+
+- [OVHcloudLLM](/typescript/framework-api-reference/classes/ovhcloudllm/)
+

e2e/examples/cloudflare-worker-agent/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.192
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.0.191
 
 ### Patch Changes

e2e/examples/cloudflare-worker-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.191",
+  "version": "0.0.192",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/next-agent-test
 
+## 0.1.192
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.1.191
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.191",
+  "version": "0.1.192",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-edge-runtime/CHANGELOG.md

@@ -1,5 +1,12 @@
 # test-edge-runtime
 
+## 0.1.191
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.1.190
 
 ### Patch Changes

e2e/examples/nextjs-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.190",
+  "version": "0.1.191",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-node-runtime/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.64
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+  - @llamaindex/huggingface@0.1.32
+
 ## 0.1.63
 
 ### Patch Changes

e2e/examples/nextjs-node-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.63",
+  "version": "0.1.64",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/vite-import-llamaindex/CHANGELOG.md

@@ -1,5 +1,12 @@
 # vite-import-llamaindex
 
+## 0.0.58
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.0.57
 
 ### Patch Changes

e2e/examples/vite-import-llamaindex/package.json

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.57",
+  "version": "0.0.58",
   "type": "module",
   "scripts": {
     "build": "vite build",

e2e/examples/waku-query-engine/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.192
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.0.191
 
 ### Patch Changes

e2e/examples/waku-query-engine/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.191",
+  "version": "0.0.192",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,5 +1,43 @@
 # examples
 
+## 0.4.0
+
+### Minor Changes
+
+- 09ba5aa: Add OVHcloud AI Endpoints provider
+- 91627dc: Update storage providers to append MongoDB client metadata
+
+### Patch Changes
+
+- fed32ab: Update vercel/ai
+- 020928c: respect Gemini's requests-per-minute rate limit with waits
+- 3af5617: fix undefined values in querytool
+- Updated dependencies [fed32ab]
+- Updated dependencies [09ba5aa]
+- Updated dependencies [020928c]
+- Updated dependencies [3af5617]
+- Updated dependencies [76709c2]
+- Updated dependencies [91627dc]
+  - @llamaindex/vercel@0.1.23
+  - @llamaindex/ovhcloud@1.0.0
+  - @llamaindex/google@0.4.0
+  - llamaindex@0.12.1
+  - @llamaindex/openai@0.4.22
+  - @llamaindex/mongodb@0.1.0
+  - @llamaindex/azure@0.2.0
+  - @llamaindex/tools@0.2.0
+  - @llamaindex/clip@0.0.78
+  - @llamaindex/deepinfra@0.0.78
+  - @llamaindex/deepseek@0.0.40
+  - @llamaindex/fireworks@0.0.38
+  - @llamaindex/groq@0.0.94
+  - @llamaindex/huggingface@0.1.32
+  - @llamaindex/jinaai@0.0.38
+  - @llamaindex/perplexity@0.0.35
+  - @llamaindex/together@0.0.38
+  - @llamaindex/vllm@0.0.64
+  - @llamaindex/xai@0.0.25
+
 ## 0.3.43
 
 ### Patch Changes

examples/agents/agent/query-tool.ts

@@ -1,12 +1,15 @@
-import { openai } from "@llamaindex/openai";
+import { OpenAIEmbedding, openai } from "@llamaindex/openai";
 import {
   agent,
   agentStreamEvent,
   agentToolCallResultEvent,
 } from "@llamaindex/workflow";
-import { Document, VectorStoreIndex } from "llamaindex";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
 
 async function main() {
+  Settings.embedModel = new OpenAIEmbedding();
+  Settings.llm = openai({ model: "gpt-4o" });
+
   const index = await VectorStoreIndex.fromDocuments([
     new Document({
       text: "Cats have a specialized collarbone that allows them to always land on their feet when they fall.",
@@ -20,7 +23,6 @@ async function main() {
   ]);
 
   const myAgent = agent({
-    llm: openai({ model: "gpt-4o" }),
     tools: [
       index.queryTool({
         options: { similarityTopK: 2 },

examples/local-settings/package.json

@@ -16,7 +16,7 @@
   },
   "dependencies": {
     "@llamaindex/openai": "^0.4.20",
-    "express": "^5.1.0",
+    "express": "^5.2.0",
     "llamaindex": "^0.12.0"
   }
 }

examples/models/gemini/embedding_ratelimits.ts

@@ -0,0 +1,20 @@
+import { GEMINI_EMBEDDING_MODEL, GeminiEmbedding } from "@llamaindex/google";
+
+const requests_per_minute_limit = 3000; // cf. https://ai.google.dev/gemini-api/docs/rate-limits
+
+async function main() {
+  if (!process.env.GOOGLE_API_KEY) {
+    throw new Error("Please set the GOOGLE_API_KEY environment variable.");
+  }
+  const embedModel = new GeminiEmbedding({
+    model: GEMINI_EMBEDDING_MODEL.EMBEDDING_001,
+  });
+  const texts = Array.from(
+    { length: requests_per_minute_limit + 1000 },
+    (_, i) => `text ${i}`,
+  );
+  const embeddings = await embedModel.getTextEmbeddingsBatch(texts);
+  console.log(`\nWe have ${embeddings.length} embeddings`);
+}
+
+main().catch(console.error);

examples/models/ovhcloud.ts

@@ -0,0 +1,50 @@
+import { OVHcloudEmbedding, OVHcloudLLM } from "@llamaindex/ovhcloud";
+
+// OVHcloud AI Endpoints can be used for free with rate limits without an API key
+// To use with an API key, set OVHCLOUD_API_KEY environment variable
+// or pass it directly in the constructor
+// To generate an API key, go to https://ovh.com/manager > Public Cloud > AI & Machine Learning > AI Endpoints > API keys
+// Visit our catalog for the list of all available models: https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/
+
+// Example 1: Using without API key (free tier with rate limits)
+const ovhcloudFree = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+  // apiKey is optional - can be omitted or set to empty string for free tier
+});
+
+// Example 2: Using with API key
+const ovhcloud = new OVHcloudLLM({
+  model: "gpt-oss-120b",
+  apiKey: process.env.OVHCLOUD_API_KEY || "",
+});
+
+(async () => {
+  console.log("Chatting with OVHcloud AI Endpoints...");
+  const generator = await ovhcloud.chat({
+    messages: [
+      {
+        role: "system",
+        content: "You are a helpful AI assistant.",
+      },
+      {
+        role: "user",
+        content: "Tell me about OVHcloud AI Endpoints",
+      },
+    ],
+    stream: true,
+  });
+
+  for await (const message of generator) {
+    process.stdout.write(message.delta);
+  }
+  console.log("\n");
+
+  // Example with embeddings
+  console.log("Getting embeddings...");
+  const embedding = new OVHcloudEmbedding({
+    model: "BGE-M3",
+  });
+  const vector = await embedding.getTextEmbedding("Hello world!");
+  console.log("Vector dimensions:", vector.length);
+  console.log("First 5 values:", vector.slice(0, 5));
+})();

examples/models/vercel/vector-store.ts

@@ -1,11 +1,13 @@
 import { openai } from "@ai-sdk/openai";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 import { llamaindex } from "@llamaindex/vercel";
 import { stepCountIs, streamText } from "ai";
-import { Document, VectorStoreIndex } from "llamaindex";
-
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
 import fs from "node:fs/promises";
 
 async function main() {
+  Settings.embedModel = new OpenAIEmbedding();
+
   const path = "node_modules/llamaindex/examples/abramov.txt";
   const essay = await fs.readFile(path, "utf-8");
   const document = new Document({ text: essay, id_: path });

examples/package.json

@@ -1,46 +1,46 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.43",
+  "version": "0.4.0",
   "private": true,
   "scripts": {
     "lint": "eslint .",
     "start": "echo 'To get started, run `npx tsx <path to example>`'"
   },
   "dependencies": {
-    "@ai-sdk/openai": "^2.0.27",
+    "@ai-sdk/openai": "^2.0.76",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
     "@llamaindex/anthropic": "^0.3.25",
     "@llamaindex/assemblyai": "^0.1.21",
     "@llamaindex/astra": "^0.0.36",
-    "@llamaindex/azure": "^0.1.38",
+    "@llamaindex/azure": "^0.2.0",
     "@llamaindex/bm25-retriever": "^0.0.11",
     "@llamaindex/chroma": "^0.0.36",
-    "@llamaindex/clip": "^0.0.77",
-    "llama-cloud-services": "^0.3.5",
+    "@llamaindex/clip": "^0.0.78",
     "@llamaindex/cohere": "^0.0.36",
     "@llamaindex/core": "^0.6.22",
-    "@llamaindex/deepinfra": "^0.0.77",
-    "@llamaindex/deepseek": "^0.0.39",
+    "@llamaindex/deepinfra": "^0.0.78",
+    "@llamaindex/deepseek": "^0.0.40",
     "@llamaindex/discord": "^0.1.21",
     "@llamaindex/elastic-search": "^0.1.22",
     "@llamaindex/env": "^0.1.30",
     "@llamaindex/firestore": "^1.0.29",
-    "@llamaindex/fireworks": "^0.0.37",
-    "@llamaindex/google": "^0.3.22",
-    "@llamaindex/groq": "^0.0.93",
-    "@llamaindex/huggingface": "^0.1.31",
-    "@llamaindex/jinaai": "^0.0.37",
+    "@llamaindex/fireworks": "^0.0.38",
+    "@llamaindex/google": "^0.4.0",
+    "@llamaindex/groq": "^0.0.94",
+    "@llamaindex/huggingface": "^0.1.32",
+    "@llamaindex/jinaai": "^0.0.38",
     "@llamaindex/milvus": "^0.1.31",
     "@llamaindex/mistral": "^0.1.22",
     "@llamaindex/mixedbread": "^0.0.36",
-    "@llamaindex/mongodb": "^0.0.37",
+    "@llamaindex/mongodb": "^0.1.0",
     "@llamaindex/node-parser": "^2.0.22",
     "@llamaindex/notion": "^0.1.21",
     "@llamaindex/ollama": "^0.1.23",
-    "@llamaindex/openai": "^0.4.21",
-    "@llamaindex/perplexity": "^0.0.34",
+    "@llamaindex/openai": "^0.4.22",
+    "@llamaindex/ovhcloud": "^1.0.0",
+    "@llamaindex/perplexity": "^0.0.35",
     "@llamaindex/pinecone": "^0.1.22",
     "@llamaindex/portkey-ai": "^0.0.64",
     "@llamaindex/postgres": "^0.0.65",
@@ -48,25 +48,26 @@
     "@llamaindex/readers": "^3.1.21",
     "@llamaindex/replicate": "^0.0.64",
     "@llamaindex/supabase": "^0.1.23",
-    "@llamaindex/together": "^0.0.37",
-    "@llamaindex/tools": "^0.1.12",
+    "@llamaindex/together": "^0.0.38",
+    "@llamaindex/tools": "^0.2.0",
     "@llamaindex/upstash": "^0.0.36",
-    "@llamaindex/vercel": "^0.1.22",
-    "@llamaindex/vllm": "^0.0.63",
+    "@llamaindex/vercel": "^0.1.23",
+    "@llamaindex/vllm": "^0.0.64",
     "@llamaindex/voyage-ai": "^1.0.28",
     "@llamaindex/weaviate": "^0.0.37",
     "@llamaindex/workflow": "^1.1.24",
-    "@llamaindex/xai": "^0.0.24",
+    "@llamaindex/xai": "^0.0.25",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
-    "ai": "^5.0.39",
+    "ai": "^5.0.106",
     "ajv": "^8.17.1",
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.12.0",
-    "mongodb": "6.7.0",
+    "llama-cloud-services": "^0.3.5",
+    "llamaindex": "^0.12.1",
+    "mongodb": "6.21.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
     "zod": "^4.1.5"

examples/pnpm-workspace.yaml

@@ -1,2 +0,0 @@
-packages:
-  - "**"

packages/autotool/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/autotool
 
+## 9.0.1
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 9.0.0
 
 ### Patch Changes

packages/autotool/examples/01_node/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.139
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+  - @llamaindex/autotool@9.0.1
+
 ## 0.0.138
 
 ### Patch Changes

packages/autotool/examples/01_node/package.json

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.138"
+  "version": "0.0.139"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "9.0.0",
+  "version": "9.0.1",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/experimental/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/experimental
 
+## 0.0.208
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+  - llamaindex@0.12.1
+
 ## 0.0.207
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.207",
+  "version": "0.0.208",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,11 @@
 # llamaindex
 
+## 0.12.1
+
+### Patch Changes
+
+- 3af5617: fix undefined values in querytool
+
 ## 0.12.0
 
 ### Minor Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.12.0",
+  "version": "0.12.1",
   "license": "MIT",
   "type": "module",
   "keywords": [

packages/llamaindex/src/tools/QueryEngineTool.ts

@@ -54,9 +54,11 @@ export class QueryEngineTool implements BaseTool<QueryEngineParam> {
       return { content: response.message.content } as unknown as JSONValue;
     }
 
+    // Use JSON.parse(JSON.stringify()) to remove undefined values from sourceNodes
+    // since undefined is not a valid JSONValue
     return {
       content: response.message.content,
-      sourceNodes: response.sourceNodes,
+      sourceNodes: JSON.parse(JSON.stringify(response.sourceNodes ?? [])),
     } as unknown as JSONValue;
   }
 }

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/core-test
 
+## 0.1.23
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.1.22
 
 ### Patch Changes

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.22",
+  "version": "0.1.23",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/clip
 
+## 0.0.78
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.77
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.77",
+  "version": "0.0.78",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/deepinfra
 
+## 0.0.78
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.77
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.77",
+  "version": "0.0.78",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/deepseek
 
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.39
 
 ### Patch Changes

packages/providers/deepseek/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepseek",
   "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.39",
+  "version": "0.0.40",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/fireworks/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/fireworks
 
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/fireworks/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/fireworks",
   "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.38",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/google
 
+## 0.4.0
+
+### Minor Changes
+
+- 020928c: respect Gemini's requests-per-minute rate limit with waits
+
 ## 0.3.22
 
 ### Patch Changes

packages/providers/google/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/google",
   "description": "Google Adapter for LlamaIndex",
-  "version": "0.3.22",
+  "version": "0.4.0",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/src/GeminiEmbedding.ts

@@ -43,12 +43,59 @@ export class GeminiEmbedding extends BaseEmbedding {
     this.embedBatchSize = opts?.embedBatchSize ?? DEFAULT_EMBED_BATCH_SIZE;
   }
 
+  // Add a retry wrapper for embedContent to handle rate limits (5s wait, up to 20 tries)
+  private async embedWithRetry(args: {
+    model: string;
+    contents: string | string[];
+  }) {
+    const MAX_TRIES = 20;
+    const DELAY_MS = 5000;
+
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    const isRateLimitError = (err: any) => {
+      if (!err) return false;
+      return (
+        err.status === 429 ||
+        err.message.indexOf('"status":"RESOURCE_EXHAUSTED"') !== -1
+      );
+    };
+    /* error looks like this
+      {"error":{"code":429,"message":"You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_paid_tier_requests, limit: 0","status":"RESOURCE_EXHAUSTED","details":[{"@type":"type.googleapis.com/google.rpc.Help","links":[{"description":"Learn more about Gemini API quotas","url":"https://ai.google.dev/gemini-api/docs/rate-limits"}]},{"@type":"type.googleapis.com/google.rpc.QuotaFailure","violations":[{"quotaMetric":"generativelanguage.googleapis.com/embed_content_paid_tier_requests","quotaId":"EmbedContentPerMinutePerProjectPerUserPerModel-PaidTier"}]}]}}
+    */
+
+    const sleep = (ms: number) => new Promise((res) => setTimeout(res, ms));
+
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    let lastErr: any = null;
+    for (let attempt = 1; attempt <= MAX_TRIES; attempt++) {
+      try {
+        return await this.ai.models.embedContent(args);
+      } catch (err) {
+        lastErr = err;
+        if (isRateLimitError(err) && attempt < MAX_TRIES) {
+          await sleep(DELAY_MS);
+          console.debug(
+            `Gemini Embeddings rate limit error encountered. Retrying attempt ${attempt}...`,
+          );
+          continue;
+        }
+        throw err;
+      }
+    }
+    // If we exit loop unexpectedly, throw the last error.
+    throw lastErr;
+  }
+
   getTextEmbeddings = async (texts: string[]) => {
-    const result = await this.ai.models.embedContent({
+    const result = await this.embedWithRetry({
       model: this.model,
       contents: texts,
     });
-    return result.embeddings?.map((embedding) => embedding.values ?? []) ?? [];
+
+    return (
+      // eslint-disable-next-line @typescript-eslint/no-explicit-any
+      result.embeddings?.map((embedding: any) => embedding.values ?? []) ?? []
+    );
   };
 
   async getTextEmbeddingsBatch(
@@ -64,7 +111,7 @@ export class GeminiEmbedding extends BaseEmbedding {
   }
 
   async getTextEmbedding(text: string): Promise<number[]> {
-    const result = await this.ai.models.embedContent({
+    const result = await this.embedWithRetry({
       model: this.model,
       contents: text,
     });

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/groq
 
+## 0.0.94
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.93
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.93",
+  "version": "0.0.94",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/huggingface
 
+## 0.1.32
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.1.31
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.1.31",
+  "version": "0.1.32",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/jinaai/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/jinaai
 
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/jinaai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/jinaai",
   "description": "JinaAI Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.38",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/openai
 
+## 0.4.22
+
+### Patch Changes
+
+- 76709c2: fix: first tool call chunk without arguments
+
 ## 0.4.21
 
 ### Patch Changes

packages/providers/openai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/openai",
   "description": "OpenAI Adapter for LlamaIndex",
-  "version": "0.4.21",
+  "version": "0.4.22",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/src/llm.ts

@@ -415,12 +415,16 @@ export class OpenAI extends ToolCallLLM<OpenAIAdditionalChatOptions> {
         toolCallMap.set(choice.delta.tool_calls[0].id, currentToolCall);
       } else {
         if (choice.delta.tool_calls?.[0]!.function?.arguments) {
+          if (typeof currentToolCall!.input !== "string") {
+            currentToolCall!.input = "";
+          }
           currentToolCall!.input +=
             choice.delta.tool_calls[0].function.arguments;
         }
       }
 
-      const isDone: boolean = choice.finish_reason !== null;
+      const isDone: boolean =
+        choice.finish_reason !== null && choice.finish_reason !== undefined;
 
       if (isDone && currentToolCall) {
         // for the last one, we need to emit the tool call

packages/providers/ovhcloud/CHANGELOG.md

@@ -0,0 +1,18 @@
+# @llamaindex/ovhcloud
+
+## 1.0.0
+
+### Major Changes
+
+- 09ba5aa: Add OVHcloud AI Endpoints provider
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
+## 0.0.1
+
+### Patch Changes
+
+- Initial release of OVHcloud AI Endpoints provider

packages/providers/ovhcloud/CLAUDE.md

@@ -0,0 +1,130 @@
+# CLAUDE.md - OVHcloud AI Endpoints Provider Package
+
+This package provides LLM and embedding integrations for OVHcloud AI Endpoints in LlamaIndex.TS.
+
+## Package Overview
+
+The `@llamaindex/ovhcloud` package offers two main components:
+
+1. **OVHcloudLLM** - OpenAI-compatible chat model interface using OVHcloud's hosted models
+2. **OVHcloudEmbedding** - OpenAI-compatible embedding API integration for text embeddings
+
+## Architecture
+
+### LLM Integration (src/llm.ts)
+
+The `OVHcloudLLM` class extends the OpenAI class from `@llamaindex/openai`, leveraging OVHcloud's OpenAI-compatible API:
+
+- **Base URL**: `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`
+- **Default Model**: `gpt-oss-120b`
+- **Authentication**: Optional - can use free tier with rate limits (empty API key) or with `OVHCLOUD_API_KEY` environment variable
+- **Implementation**: Wrapper around OpenAI class with OVHcloud-specific defaults
+
+### Embedding Integration (src/embedding.ts)
+
+The `OVHcloudEmbedding` class extends the `OpenAIEmbedding` class:
+
+- **Base URL**: `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`
+- **Default Model**: `BGE-M3`
+- **Authentication**: Optional - can use free tier with rate limits (empty API key) or with `OVHCLOUD_API_KEY` environment variable
+- **Implementation**: Wrapper around OpenAIEmbedding class with OVHcloud-specific defaults
+
+## Configuration
+
+### Environment Variables
+
+- `OVHCLOUD_API_KEY` - Optional API key. If not provided or empty, uses free tier with rate limits
+
+### LLM Configuration
+
+```typescript
+import { OVHcloudLLM } from "@llamaindex/ovhcloud";
+
+// Free tier (no API key required)
+const llm = new OVHcloudLLM({
+  model: "gpt-oss-120b", // optional
+  // apiKey omitted or empty string for free tier
+});
+
+// With API key
+const llm = new OVHcloudLLM({
+  model: "gpt-oss-120b", // optional
+  apiKey: "your-api-key", // optional if OVHCLOUD_API_KEY is set
+  // ... other OpenAI-compatible options
+});
+```
+
+### Embedding Configuration
+
+```typescript
+import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
+
+// Free tier (no API key required)
+const embedding = new OVHcloudEmbedding({
+  model: "BGE-M3", // optional
+  // apiKey omitted or empty string for free tier
+});
+
+// With API key
+const embedding = new OVHcloudEmbedding({
+  model: "BGE-M3", // optional
+  apiKey: "your-api-key", // optional if OVHCLOUD_API_KEY is set
+  // ... other OpenAI-compatible options
+});
+```
+
+## Key Features
+
+### LLM Features
+
+- Full OpenAI API compatibility through inheritance
+- Optional API key management (supports free tier with rate limits)
+- Support for all OVHcloud hosted models
+- Default base URL configured for OVHcloud endpoints
+
+### Embedding Features
+
+- Full OpenAI API compatibility through inheritance
+- Optional API key management (supports free tier with rate limits)
+- Support for OpenAI-compatible embedding models
+- Default base URL configured for OVHcloud endpoints
+
+## Free Tier Support
+
+OVHcloud AI Endpoints can be used for free with rate limits by:
+
+- Omitting the `apiKey` parameter
+- Setting `apiKey` to an empty string
+- Not setting the `OVHCLOUD_API_KEY` environment variable
+
+For higher rate limits, generate an API key from:
+
+- OVHcloud Manager: https://ovh.com/manager
+- Navigate to: Public Cloud → AI & Machine Learning → AI Endpoints → API keys
+
+## Dependencies
+
+- `@llamaindex/core` - Core interfaces and utilities
+- `@llamaindex/env` - Environment variable handling
+- `@llamaindex/openai` - OpenAI implementation (for both LLM and embedding)
+
+## Development
+
+- **Build**: `pnpm build` (uses bunchee)
+- **Watch**: `pnpm dev` (uses bunchee --watch)
+- **Test**: `pnpm test` (uses vitest)
+- **Output**: Dual CJS/ESM exports in `dist/`
+
+## API Endpoints
+
+- **Base URL**: `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`
+- **Catalog**: https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/
+- **Documentation**: https://www.ovhcloud.com/en/public-cloud/ai-endpoints/
+
+## Resources
+
+- [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/)
+- [OVHcloud Manager](https://ovh.com/manager)
+- [OVHcloud AI Endpoints Documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/)
+
+This package follows the LlamaIndex.TS provider pattern, implementing standard interfaces while providing OVHcloud-specific configuration and free tier support.

packages/providers/ovhcloud/package.json

@@ -0,0 +1,46 @@
+{
+  "name": "@llamaindex/ovhcloud",
+  "description": "OVHcloud AI Endpoints Adapter for LlamaIndex",
+  "version": "1.0.0",
+  "type": "module",
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
+  "exports": {
+    ".": {
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      },
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      }
+    }
+  },
+  "files": [
+    "dist"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+    "directory": "packages/providers/ovhcloud"
+  },
+  "scripts": {
+    "build": "bunchee",
+    "dev": "bunchee --watch",
+    "test": "vitest run"
+  },
+  "dependencies": {
+    "@llamaindex/env": "workspace:*",
+    "@llamaindex/openai": "workspace:*"
+  },
+  "devDependencies": {
+    "vitest": "^2.1.5",
+    "@llamaindex/core": "workspace:*",
+    "@llamaindex/env": "workspace:*"
+  },
+  "peerDependencies": {
+    "@llamaindex/core": "workspace:*",
+    "@llamaindex/env": "workspace:*"
+  }
+}

packages/providers/ovhcloud/src/embedding.ts

@@ -0,0 +1,27 @@
+import { getEnv } from "@llamaindex/env";
+import { OpenAIEmbedding } from "@llamaindex/openai";
+import { BASE_URL, ENV_VARIABLE_NAME } from "./utils";
+
+export class OVHcloudEmbedding extends OpenAIEmbedding {
+  constructor(init?: Omit<Partial<OpenAIEmbedding>, "session">) {
+    const {
+      apiKey = getEnv(ENV_VARIABLE_NAME) ?? "",
+      additionalSessionOptions = {},
+      model = "BGE-M3",
+      ...rest
+    } = init ?? {};
+
+    // OVHcloud allows empty API key for free tier with rate limits
+    // So we don't throw an error if apiKey is empty or undefined
+
+    additionalSessionOptions.baseURL =
+      additionalSessionOptions.baseURL ?? BASE_URL;
+
+    super({
+      apiKey: apiKey || "", // Use empty string if not provided
+      additionalSessionOptions,
+      model,
+      ...rest,
+    });
+  }
+}

packages/providers/ovhcloud/src/index.ts

@@ -0,0 +1,2 @@
+export * from "./embedding";
+export * from "./llm";

packages/providers/ovhcloud/src/llm.ts

@@ -0,0 +1,35 @@
+import { getEnv } from "@llamaindex/env";
+import { OpenAI } from "@llamaindex/openai";
+import { BASE_URL, ENV_VARIABLE_NAME } from "./utils";
+
+export class OVHcloudLLM extends OpenAI {
+  constructor(init?: Omit<Partial<OpenAI>, "session">) {
+    const {
+      apiKey = getEnv(ENV_VARIABLE_NAME) ?? "",
+      additionalSessionOptions = {},
+      model = "gpt-oss-120b",
+      ...rest
+    } = init ?? {};
+
+    // OVHcloud allows empty API key for free tier with rate limits
+    // So we don't throw an error if apiKey is empty or undefined
+
+    additionalSessionOptions.baseURL =
+      additionalSessionOptions.baseURL ?? BASE_URL;
+
+    super({
+      apiKey: apiKey || "", // Use empty string if not provided
+      additionalSessionOptions,
+      model,
+      ...rest,
+    });
+  }
+}
+
+/**
+ * Convenience function to create a new OVHcloudLLM instance.
+ * @param init - Optional initialization parameters for the OVHcloudLLM instance.
+ * @returns A new OVHcloudLLM instance.
+ */
+export const ovhcloud = (init?: ConstructorParameters<typeof OVHcloudLLM>[0]) =>
+  new OVHcloudLLM(init);

packages/providers/ovhcloud/src/utils.ts

@@ -0,0 +1,2 @@
+export const ENV_VARIABLE_NAME = "OVHCLOUD_API_KEY";
+export const BASE_URL = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1";

packages/providers/ovhcloud/tests/index.test.ts

@@ -0,0 +1,145 @@
+import type { ChatMessage } from "@llamaindex/core/llms";
+import { setEnvs } from "@llamaindex/env";
+import { describe, expect, test } from "vitest";
+import { OVHcloudEmbedding, OVHcloudLLM } from "../src/index";
+import { BASE_URL } from "../src/utils";
+
+describe("OVHcloudLLM", () => {
+  describe("Initialization", () => {
+    test("should initialize without API key (free tier)", () => {
+      const llm = new OVHcloudLLM({
+        model: "gpt-oss-120b",
+      });
+      expect(llm).toBeInstanceOf(OVHcloudLLM);
+      expect(llm.model).toBe("gpt-oss-120b");
+    });
+
+    test("should initialize with empty API key (free tier)", () => {
+      const llm = new OVHcloudLLM({
+        model: "gpt-oss-120b",
+        apiKey: "",
+      });
+      expect(llm).toBeInstanceOf(OVHcloudLLM);
+    });
+
+    test("should initialize with API key from environment", () => {
+      setEnvs({
+        OVHCLOUD_API_KEY: "test-api-key",
+      });
+      const llm = new OVHcloudLLM({
+        model: "gpt-oss-120b",
+      });
+      expect(llm).toBeInstanceOf(OVHcloudLLM);
+    });
+
+    test("should initialize with explicit API key", () => {
+      const llm = new OVHcloudLLM({
+        model: "gpt-oss-120b",
+        apiKey: "explicit-api-key",
+      });
+      expect(llm).toBeInstanceOf(OVHcloudLLM);
+    });
+
+    test("should use default model if not specified", () => {
+      const llm = new OVHcloudLLM();
+      expect(llm.model).toBe("gpt-oss-120b");
+    });
+
+    test("should use custom base URL if provided", () => {
+      const customBaseURL = "https://custom.endpoint.com/v1";
+      const llm = new OVHcloudLLM({
+        additionalSessionOptions: {
+          baseURL: customBaseURL,
+        },
+      });
+      expect(llm.additionalSessionOptions?.baseURL).toBe(customBaseURL);
+    });
+  });
+
+  describe("Base URL Configuration", () => {
+    test("should use default OVHcloud base URL", () => {
+      const llm = new OVHcloudLLM();
+      expect(llm.additionalSessionOptions?.baseURL).toBe(BASE_URL);
+    });
+  });
+
+  describe("Message Formatting", () => {
+    test("should format basic messages correctly", () => {
+      const llm = new OVHcloudLLM();
+      const inputMessages: ChatMessage[] = [
+        {
+          content: "You are a helpful assistant.",
+          role: "system",
+        },
+        {
+          content: "Hello?",
+          role: "user",
+        },
+      ];
+
+      // OVHcloudLLM extends OpenAI, so it uses OpenAI's message formatting
+      // We just verify the instance is created correctly
+      expect(llm).toBeInstanceOf(OVHcloudLLM);
+    });
+  });
+});
+
+describe("OVHcloudEmbedding", () => {
+  describe("Initialization", () => {
+    test("should initialize without API key (free tier)", () => {
+      const embedding = new OVHcloudEmbedding({
+        model: "BGE-M3",
+      });
+      expect(embedding).toBeInstanceOf(OVHcloudEmbedding);
+      expect(embedding.model).toBe("BGE-M3");
+    });
+
+    test("should initialize with empty API key (free tier)", () => {
+      const embedding = new OVHcloudEmbedding({
+        model: "BGE-M3",
+        apiKey: "",
+      });
+      expect(embedding).toBeInstanceOf(OVHcloudEmbedding);
+    });
+
+    test("should initialize with API key from environment", () => {
+      setEnvs({
+        OVHCLOUD_API_KEY: "test-api-key",
+      });
+      const embedding = new OVHcloudEmbedding({
+        model: "BGE-M3",
+      });
+      expect(embedding).toBeInstanceOf(OVHcloudEmbedding);
+    });
+
+    test("should initialize with explicit API key", () => {
+      const embedding = new OVHcloudEmbedding({
+        model: "BGE-M3",
+        apiKey: "explicit-api-key",
+      });
+      expect(embedding).toBeInstanceOf(OVHcloudEmbedding);
+    });
+
+    test("should use default model if not specified", () => {
+      const embedding = new OVHcloudEmbedding();
+      expect(embedding.model).toBe("BGE-M3");
+    });
+
+    test("should use custom base URL if provided", () => {
+      const customBaseURL = "https://custom.endpoint.com/v1";
+      const embedding = new OVHcloudEmbedding({
+        additionalSessionOptions: {
+          baseURL: customBaseURL,
+        },
+      });
+      expect(embedding.additionalSessionOptions?.baseURL).toBe(customBaseURL);
+    });
+  });
+
+  describe("Base URL Configuration", () => {
+    test("should use default OVHcloud base URL", () => {
+      const embedding = new OVHcloudEmbedding();
+      expect(embedding.additionalSessionOptions?.baseURL).toBe(BASE_URL);
+    });
+  });
+});

packages/providers/ovhcloud/tsconfig.json

@@ -0,0 +1,19 @@
+{
+  "extends": "../../../tsconfig.json",
+  "compilerOptions": {
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "outDir": "./lib",
+    "tsBuildInfoFile": "./lib/.tsbuildinfo"
+  },
+  "include": ["./src"],
+  "references": [
+    {
+      "path": "../openai/tsconfig.json"
+    },
+    {
+      "path": "../../env/tsconfig.json"
+    }
+  ]
+}

packages/providers/perplexity/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/perplexity
 
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.34
 
 ### Patch Changes

packages/providers/perplexity/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/perplexity",
   "description": "Perplexity Adapter for LlamaIndex",
-  "version": "0.0.34",
+  "version": "0.0.35",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/storage/azure/CHANGELOG.md

@@ -1,5 +1,16 @@
 # @llamaindex/azure
 
+## 0.2.0
+
+### Minor Changes
+
+- 91627dc: Update storage providers to append MongoDB client metadata
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.1.38
 
 ### Patch Changes

packages/providers/storage/azure/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/azure",
   "description": "Azure Storage for LlamaIndex",
-  "version": "0.1.38",
+  "version": "0.2.0",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -72,7 +72,7 @@
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
     "@llamaindex/openai": "workspace:*",
-    "mongodb": "^6.7.0",
+    "mongodb": "^6.21.0",
     "openai": "^4.90.0"
   }
 }

packages/providers/storage/azure/src/chatStore/AzureCosmosMongovCoreChatStore.ts

@@ -7,6 +7,8 @@ import type {
 import { BaseChatStore } from "@llamaindex/core/storage/chat-store";
 import type { Collection } from "mongodb";
 import { MongoClient } from "mongodb";
+import pkg from "../../package.json";
+
 const DEFAULT_CHAT_DATABASE = "ChatStoreDB";
 const DEFAULT_CHAT_Collection = "ChatStoreCollection";
 
@@ -40,6 +42,10 @@ export class AzureCosmosVCoreChatStore<
         "MongoClient is required for AzureCosmosVCoreChatStore initialization",
       );
     }
+    mongoClient.appendMetadata({
+      name: "LLAMAINDEX_AZURE_COSMOS_VCORE_CHAT_STORE",
+      version: pkg.version,
+    });
     this.mongoClient = mongoClient;
     this.dbName = dbName;
     this.collectionName = collectionName;

packages/providers/storage/azure/src/kvStore/AzureCosmosMongovCoreKVStore.ts

@@ -2,6 +2,7 @@
 import { BaseKVStore } from "@llamaindex/core/storage/kv-store";
 import type { Collection } from "mongodb";
 import { MongoClient } from "mongodb";
+import pkg from "../../package.json";
 const DEFAULT_CHAT_DATABASE = "KVStoreDB";
 const DEFAULT_CHAT_Collection = "KVStoreCollection";
 
@@ -38,6 +39,10 @@ export class AzureCosmosVCoreKVStore extends BaseKVStore {
         "MongoClient is required for AzureCosmosDBNoSQLVectorStore initialization",
       );
     }
+    mongoClient.appendMetadata({
+      name: "LLAMAINDEX_AZURE_COSMOS_VCORE_KV_STORE",
+      version: pkg.version,
+    });
     this.mongoClient = mongoClient;
     this.dbName = dbName;
     this.collectionName = collectionName;

packages/providers/storage/azure/src/vectorStore/AzureCosmosDBMongoVectorStore.ts

@@ -10,6 +10,7 @@ import {
 } from "@llamaindex/core/vector-store";
 import { getEnv } from "@llamaindex/env";
 import { Collection, Db, MongoClient } from "mongodb";
+import pkg from "../../package.json";
 
 /** Azure Cosmos DB for MongoDB vCore Similarity type. */
 export const AzureCosmosDBMongoDBSimilarityType = {
@@ -124,6 +125,10 @@ export class AzureCosmosDBMongoDBVectorStore extends BaseVectorStore {
         appName: "LLAMAINDEX_JS",
       });
     }
+    this.mongodbClient.appendMetadata({
+      name: "LLAMAINDEX_AZURE_COSMOS_VCORE_VECTOR_STORE",
+      version: pkg.version,
+    });
 
     this.dbName = init.dbName ?? "documentsDB";
     this.collectionName = init.collectionName ?? "documents";

packages/providers/storage/mongodb/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/mongodb
 
+## 0.1.0
+
+### Minor Changes
+
+- 91627dc: Update storage providers to append MongoDB client metadata
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/storage/mongodb/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mongodb",
   "description": "MongoDB Storage for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.1.0",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -49,6 +49,6 @@
     "@llamaindex/env": "workspace:*"
   },
   "dependencies": {
-    "mongodb": "6.7.0"
+    "mongodb": "6.21.0"
   }
 }

packages/providers/storage/mongodb/src/MongoDBAtlasVectorStore.ts

@@ -16,6 +16,7 @@ import {
 import { getEnv } from "@llamaindex/env";
 import type { BulkWriteOptions, Collection } from "mongodb";
 import { MongoClient } from "mongodb";
+import pkg from "../package.json";
 
 // define your Atlas Search index. See detail https://www.mongodb.com/docs/atlas/atlas-search/field-types/knn-vector/
 const DEFAULT_EMBEDDING_DEFINITION = {
@@ -162,6 +163,10 @@ export class MongoDBAtlasVectorSearch extends BaseVectorStore {
 
     this.dbName = init.dbName ?? "default_db";
     this.collectionName = init.collectionName ?? "default_collection";
+    this.mongodbClient.appendMetadata({
+      name: "LLAMAINDEX_MONGODB_ATLAS_VECTOR_STORE",
+      version: pkg.version,
+    });
     this.autoCreateIndex = init.autoCreateIndex ?? true;
     this.indexedMetadataFields = init.indexedMetadataFields ?? [];
     this.embeddingDefinition = {

packages/providers/storage/mongodb/src/docStore/MongoDBDocumentStore.ts

@@ -1,5 +1,6 @@
 import { KVDocumentStore } from "@llamaindex/core/storage/doc-store";
 import { MongoClient } from "mongodb";
+import pkg from "../../package.json";
 import { MongoKVStore } from "../kvStore/MongoKVStore";
 
 const DEFAULT_DATABASE = "DocumentStoreDB";
@@ -36,6 +37,10 @@ export class MongoDocumentStore extends KVDocumentStore {
       mongoClient,
       dbName,
     });
+    mongoClient.appendMetadata({
+      name: "LLAMAINDEX_MONGODB_DOC_STORE",
+      version: pkg.version,
+    });
 
     return new MongoDocumentStore({
       mongoKVStore,

packages/providers/storage/mongodb/src/kvStore/MongoKVStore.ts

@@ -24,6 +24,9 @@ export class MongoKVStore extends BaseKVStore {
 
     this.mongoClient = mongoClient;
     this.dbName = dbName;
+    this.mongoClient.appendMetadata({
+      name: "LLAMAINDEX_MONGODB_KV_STORE",
+    });
   }
 
   get client(): MongoClient {

packages/providers/storage/mongodb/src/tests/MongoDocumentStore.test.ts

@@ -1,6 +1,16 @@
 import { Document, MetadataMode } from "@llamaindex/core/schema";
-import { MongoClient } from "mongodb";
-import { afterAll, beforeAll, beforeEach, describe, expect, it } from "vitest";
+import { MongoClient, type DriverInfo } from "mongodb";
+import {
+  afterAll,
+  beforeAll,
+  beforeEach,
+  describe,
+  expect,
+  it,
+  vi,
+  type MockInstance,
+} from "vitest";
+import pkg from "../../package.json";
 import { MongoDocumentStore } from "../docStore/MongoDBDocumentStore";
 import { setupTestDb } from "./setuptTestDb";
 
@@ -9,11 +19,13 @@ describe("MongoDocumentStore", () => {
   let mongoClient: MongoClient;
   let documentStore: MongoDocumentStore;
   let mongoUri: string;
+  let appendMetadataSpy: MockInstance<(driverInfo: DriverInfo) => void>;
 
   beforeAll(async () => {
     const testDb = await setupTestDb();
     cleanup = testDb.cleanup;
     mongoClient = testDb.mongoClient;
+    appendMetadataSpy = vi.spyOn(mongoClient, "appendMetadata");
     mongoUri = testDb.mongoUri;
     documentStore = MongoDocumentStore.fromMongoClient(mongoClient);
   }, 120000);
@@ -26,6 +38,10 @@ describe("MongoDocumentStore", () => {
     it("should create instance with mongoClient", () => {
       const store = MongoDocumentStore.fromMongoClient(mongoClient);
       expect(store).toBeInstanceOf(MongoDocumentStore);
+      expect(appendMetadataSpy).toHaveBeenCalledWith({
+        name: "LLAMAINDEX_MONGODB_DOC_STORE",
+        version: pkg.version,
+      });
     });
 
     it("should create instance with custom namespace", () => {
@@ -35,6 +51,10 @@ describe("MongoDocumentStore", () => {
         "namespace",
       );
       expect(store).toBeInstanceOf(MongoDocumentStore);
+      expect(appendMetadataSpy).toHaveBeenCalledWith({
+        name: "LLAMAINDEX_MONGODB_DOC_STORE",
+        version: pkg.version,
+      });
     });
   });
 
@@ -47,6 +67,10 @@ describe("MongoDocumentStore", () => {
     it("should create instance from MongoClient", () => {
       const store = MongoDocumentStore.fromMongoClient(mongoClient);
       expect(store).toBeInstanceOf(MongoDocumentStore);
+      expect(appendMetadataSpy).toHaveBeenCalledWith({
+        name: "LLAMAINDEX_MONGODB_DOC_STORE",
+        version: pkg.version,
+      });
     });
   });
 

packages/providers/storage/mongodb/src/tests/MongokVStore.test.ts

@@ -1,5 +1,14 @@
-import type { MongoClient } from "mongodb";
-import { afterAll, beforeAll, beforeEach, describe, expect, it } from "vitest";
+import type { DriverInfo, MongoClient } from "mongodb";
+import {
+  afterAll,
+  beforeAll,
+  beforeEach,
+  describe,
+  expect,
+  it,
+  vi,
+  type MockInstance,
+} from "vitest";
 import { MongoKVStore } from "../kvStore/MongoKVStore";
 import { setupTestDb } from "./setuptTestDb";
 
@@ -8,11 +17,13 @@ describe("MongoKVStore", () => {
   let mongoClient: MongoClient;
   let mongoUri: string;
   let kvStore: MongoKVStore;
+  let appendMetadataSpy: MockInstance<(driverInfo: DriverInfo) => void>;
 
   beforeAll(async () => {
     const testDb = await setupTestDb();
     cleanUp = testDb.cleanup;
     mongoClient = testDb.mongoClient;
+    appendMetadataSpy = vi.spyOn(mongoClient, "appendMetadata");
     mongoUri = testDb.mongoUri;
     kvStore = new MongoKVStore({
       mongoClient,
@@ -32,6 +43,9 @@ describe("MongoKVStore", () => {
       });
 
       expect(kvStore).toBeInstanceOf(MongoKVStore);
+      expect(appendMetadataSpy).toHaveBeenCalledWith({
+        name: "LLAMAINDEX_MONGODB_KV_STORE",
+      });
     });
 
     it("should create db with custom db and collection name", () => {
@@ -41,6 +55,9 @@ describe("MongoKVStore", () => {
       });
 
       expect(kvStore).toBeInstanceOf(MongoKVStore);
+      expect(appendMetadataSpy).toHaveBeenCalledWith({
+        name: "LLAMAINDEX_MONGODB_KV_STORE",
+      });
     });
   });
 

packages/providers/storage/mongodb/tsconfig.json

@@ -7,7 +7,7 @@
     "outDir": "./lib",
     "tsBuildInfoFile": "./lib/.tsbuildinfo"
   },
-  "include": ["./src"],
+  "include": ["./src", "package.json"],
   "references": [
     {
       "path": "../../../core/tsconfig.json"

packages/providers/together/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/together
 
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/together/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/together",
   "description": "Together Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.38",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/vercel/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/vercel
 
+## 0.1.23
+
+### Patch Changes
+
+- fed32ab: Update vercel/ai
+
 ## 0.1.22
 
 ### Patch Changes

packages/providers/vercel/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/vercel",
   "description": "Vercel Adapter for LlamaIndex",
-  "version": "0.1.22",
+  "version": "0.1.23",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -40,7 +40,7 @@
   },
   "devDependencies": {
     "@llamaindex/core": "workspace:*",
-    "ai": "^5.0.39",
+    "ai": "^5.0.106",
     "vitest": "^2.1.5"
   },
   "peerDependencies": {

packages/providers/vllm/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/vllm
 
+## 0.0.64
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.63
 
 ### Patch Changes

packages/providers/vllm/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/vllm",
   "description": "vLLM Adapter for LlamaIndex",
-  "version": "0.0.63",
+  "version": "0.0.64",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/xai/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/xai
 
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
 ## 0.0.24
 
 ### Patch Changes

packages/providers/xai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/xai",
   "description": "XAI Adapter for LlamaIndex",
-  "version": "0.0.24",
+  "version": "0.0.25",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/tools/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/tools
 
+## 0.2.0
+
+### Minor Changes
+
+- 91627dc: Update storage providers to append MongoDB client metadata
+
 ## 0.1.12
 
 ### Patch Changes

packages/tools/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/tools",
   "description": "LlamaIndex Tools",
-  "version": "0.1.12",
+  "version": "0.2.0",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/tools/tests/wiki.test.ts

@@ -1,15 +0,0 @@
-import { describe, expect, test } from "vitest";
-import { wiki } from "../src/tools/wiki";
-
-describe("Wikipedia Tool", () => {
-  test("wiki tool returns content for valid query", async () => {
-    const wikipediaTool = wiki();
-    const result = await wikipediaTool.call({
-      query: "Albert Einstein",
-      lang: "en",
-    });
-
-    expect(result).toHaveProperty("title");
-    expect(result).toHaveProperty("content");
-  });
-});

unit/CHANGELOG.md

@@ -1,5 +1,14 @@
 # @llamaindex/unit-test
 
+## 0.1.64
+
+### Patch Changes
+
+- Updated dependencies [3af5617]
+- Updated dependencies [76709c2]
+  - llamaindex@0.12.1
+  - @llamaindex/openai@0.4.22
+
 ## 0.1.63
 
 ### Patch Changes

unit/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/unit-test",
   "private": true,
-  "version": "0.1.63",
+  "version": "0.1.64",
   "type": "module",
   "scripts": {
     "test": "vitest run"