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/migration/deprecated/agent/index.mdx

@@ -23,6 +23,6 @@ LlamaIndex.TS comes with a few built-in agents, but you can also create your own
 
 ## Api References
 
-- [OpenAIAgent](/docs/api/classes/OpenAIAgent)
-- [AnthropicAgent](/docs/api/classes/AnthropicAgent)
-- [ReActAgent](/docs/api/classes/ReActAgent)
+- [OpenAIAgent](/typescript/framework-api-reference/classes/openaiagent/)
+- [AnthropicAgent](/typescript/framework-api-reference/classes/anthropicagent/)
+- [ReActAgent](/typescript/framework-api-reference/classes/reactagent/)

docs/src/content/docs/framework/modules/agents/workflows.mdx

@@ -12,7 +12,7 @@ To use workflows install this package:
 npm i @llamaindex/workflow-core
 ```
 
-This contains the core functionality for the workflow system. You can read more about the core concepts in the [workflow-core](/docs/workflows) section.
+This contains the core functionality for the workflow system. You can read more about the core concepts in the [workflow-core](/typescript/workflows/) section.
 
 In contrast, the `@llamaindex/workflow` package contains more utiltities, such as prebuilt agents.
 

docs/src/content/docs/framework/modules/data/data_index/index.mdx

@@ -19,6 +19,6 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 
 ## API Reference
 
-- [SummaryIndex](/docs/api/classes/SummaryIndex)
-- [VectorStoreIndex](/docs/api/classes/VectorStoreIndex)
-- [KeywordTableIndex](/docs/api/classes/KeywordTableIndex)
+- [SummaryIndex](/typescript/framework-api-reference/classes/summaryindex/)
+- [VectorStoreIndex](/typescript/framework-api-reference/classes/vectorstoreindex/)
+- [KeywordTableIndex](/typescript/framework-api-reference/classes/keywordtableindex/)

docs/src/content/docs/framework/modules/data/index.mdx

@@ -13,5 +13,5 @@ document = new Document({ text: "text", metadata: { key: "val" } });
 
 ## API Reference
 
-- [Document](/docs/api/classes/Document)
-- [TextNode](/docs/api/classes/TextNode)
+- [Document](/typescript/framework-api-reference/classes/document/)
+- [TextNode](/typescript/framework-api-reference/classes/textnode/)

docs/src/content/docs/framework/modules/data/ingestion_pipeline/index.mdx

@@ -107,4 +107,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [IngestionPipeline](/docs/api/classes/IngestionPipeline)
+- [IngestionPipeline](/typescript/framework-api-reference/classes/ingestionpipeline/)

docs/src/content/docs/framework/modules/data/ingestion_pipeline/transformations/index.mdx

@@ -80,4 +80,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [TransformComponent](/docs/api/classes/TransformComponent)
+- [TransformComponent](/typescript/framework-api-reference/classes/transformcomponent/)

docs/src/content/docs/framework/modules/data/ingestion_pipeline/transformations/metadata_extraction.mdx

@@ -43,7 +43,7 @@ main().then(() => console.log("done"));
 
 ## API Reference
 
-- [SummaryExtractor](/docs/api/classes/SummaryExtractor)
-- [QuestionsAnsweredExtractor](/docs/api/classes/QuestionsAnsweredExtractor)
-- [TitleExtractor](/docs/api/classes/TitleExtractor)
-- [KeywordExtractor](/docs/api/classes/KeywordExtractor)
+- [SummaryExtractor](/typescript/framework-api-reference/classes/summaryextractor/)
+- [QuestionsAnsweredExtractor](/typescript/framework-api-reference/classes/questionsansweredextractor/)
+- [TitleExtractor](/typescript/framework-api-reference/classes/titleextractor/)
+- [KeywordExtractor](/typescript/framework-api-reference/classes/keywordextractor/)

docs/src/content/docs/framework/modules/data/ingestion_pipeline/transformations/node-parser.mdx

@@ -195,6 +195,6 @@ Try it out ⬇️
 
 ## API Reference
 
-- [SentenceSplitter](/docs/api/classes/SentenceSplitter)
-- [MarkdownNodeParser](/docs/api/classes/MarkdownNodeParser)
-- [CodeSplitter](/docs/api/classes/CodeSplitter)
+- [SentenceSplitter](/typescript/framework-api-reference/classes/sentencesplitter/)
+- [MarkdownNodeParser](/typescript/framework-api-reference/classes/markdownnodeparser/)
+- [CodeSplitter](/typescript/framework-api-reference/classes/codesplitter/)

docs/src/content/docs/framework/modules/data/readers/discord.mdx

@@ -36,4 +36,4 @@ Copy the URL in your browser and select the server you want your bot to join.
 
 ## API Reference
 
-- [DiscordReader](/docs/api/classes/DiscordReader)
+- [DiscordReader](/typescript/framework-api-reference/classes/discordreader/)

docs/src/content/docs/framework/modules/data/readers/index.mdx

@@ -48,13 +48,13 @@ It is a simple reader that reads all files from a directory and its subdirectori
 
 Currently, the following readers are mapped to specific file types:
 
-- [TextFileReader](/docs/api/classes/TextFileReader): `.txt`
-- [PDFReader](/docs/api/classes/PDFReader): `.pdf`
-- [CSVReader](/docs/api/classes/CSVReader): `.csv`
-- [MarkdownReader](/docs/api/classes/MarkdownReader): `.md`
-- [DocxReader](/docs/api/classes/DocxReader): `.docx`
-- [HTMLReader](/docs/api/classes/HTMLReader): `.htm`, `.html`
-- [ImageReader](/docs/api/classes/ImageReader): `.jpg`, `.jpeg`, `.png`, `.gif`
+- [TextFileReader](/typescript/framework-api-reference/classes/textfilereader/): `.txt`
+- [PDFReader](/typescript/framework-api-reference/classes/pdfreader/): `.pdf`
+- [CSVReader](/typescript/framework-api-reference/classes/csvreader/): `.csv`
+- [MarkdownReader](/typescript/framework-api-reference/classes/markdownreader/): `.md`
+- [DocxReader](/typescript/framework-api-reference/classes/docxreader/): `.docx`
+- [HTMLReader](/typescript/framework-api-reference/classes/htmlreader/): `.htm`, `.html`
+- [ImageReader](/typescript/framework-api-reference/classes/imagereader/): `.jpg`, `.jpeg`, `.png`, `.gif`
 
 You can modify the reader three different ways:
 
@@ -118,4 +118,4 @@ const text = csv.getText()
 
 ## API Reference
 
-- [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)
+- [SimpleDirectoryReader](/typescript/framework-api-reference/classes/simpledirectoryreader/)

docs/src/content/docs/framework/modules/data/readers/json.mdx

@@ -152,4 +152,4 @@ Output:
 
 ## API Reference
 
-- [JSONReader](/docs/api/classes/JSONReader)
+- [JSONReader](/typescript/framework-api-reference/classes/jsonreader/)

docs/src/content/docs/framework/modules/data/readers/llama_parse/index.mdx

@@ -60,4 +60,4 @@ Below a full example of `LlamaParse` integrated in `SimpleDirectoryReader` with
 
 ## API Reference
 
-- [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)
+- [SimpleDirectoryReader](/typescript/framework-api-reference/classes/simpledirectoryreader/)

docs/src/content/docs/framework/modules/data/readers/llama_parse/json_mode.mdx

@@ -98,4 +98,4 @@ You can assign any other values of the JSON response to the Document as needed.
 
 ## API Reference
 
-- [SimpleDirectoryReader](/docs/api/classes/SimpleDirectoryReader)
+- [SimpleDirectoryReader](/typescript/framework-api-reference/classes/simpledirectoryreader/)

docs/src/content/docs/framework/modules/data/stores/chat_stores/index.mdx

@@ -6,11 +6,11 @@ Chat stores manage chat history by storing sequences of messages in a structured
 
 ## Available Chat Stores
 
-- [SimpleChatStore](/docs/api/classes/SimpleChatStore): A simple in-memory chat store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [SimpleChatStore](/typescript/framework-api-reference/classes/simplechatstore/): A simple in-memory chat store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## API Reference
 
-- [BaseChatStore](/docs/api/classes/BaseChatStore)
+- [BaseChatStore](/typescript/framework-api-reference/classes/basechatstore/)
 

docs/src/content/docs/framework/modules/data/stores/doc_stores/index.mdx

@@ -6,8 +6,8 @@ Document stores contain ingested document chunks, i.e. [Node](/typescript/framew
 
 ## Available Document Stores
 
-- [SimpleDocumentStore](/docs/api/classes/SimpleDocumentStore): A simple in-memory document store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
-- [PostgresDocumentStore](/docs/api/classes/PostgresDocumentStore): A PostgreSQL document store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
+- [SimpleDocumentStore](/typescript/framework-api-reference/classes/simpledocumentstore/): A simple in-memory document store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresDocumentStore](/typescript/framework-api-reference/classes/postgresdocumentstore/): A PostgreSQL document store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
@@ -33,4 +33,4 @@ const storageContext = await storageContextFromDefaults({
 
 ## API Reference
 
-- [BaseDocumentStore](/docs/api/classes/BaseDocumentStore)
+- [BaseDocumentStore](/typescript/framework-api-reference/classes/basedocumentstore/)

docs/src/content/docs/framework/modules/data/stores/index.mdx

@@ -32,4 +32,4 @@ const index = await VectorStoreIndex.fromDocuments([document], {
 
 ## API Reference
 
-- [StorageContext](/docs/api/interfaces/StorageContext)
+- [StorageContext](/typescript/framework-api-reference/interfaces/storagecontext)

docs/src/content/docs/framework/modules/data/stores/index_stores/index.mdx

@@ -6,8 +6,8 @@ Index stores are underlying storage components that contain metadata(i.e. inform
 
 ## Available Index Stores
 
-- [SimpleIndexStore](/docs/api/classes/SimpleIndexStore): A simple in-memory index store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
-- [PostgresIndexStore](/docs/api/classes/PostgresIndexStore): A PostgreSQL index store, , see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
+- [SimpleIndexStore](/typescript/framework-api-reference/classes/simpleindexstore/): A simple in-memory index store with support for [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresIndexStore](/typescript/framework-api-reference/classes/postgresindexstore/): A PostgreSQL index store, , see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
@@ -33,4 +33,4 @@ const storageContext = await storageContextFromDefaults({
 
 ## API Reference
 
-- [BaseIndexStore](/docs/api/classes/BaseIndexStore)
+- [BaseIndexStore](/typescript/framework-api-reference/classes/baseindexstore/)

docs/src/content/docs/framework/modules/data/stores/kv_stores/index.mdx

@@ -6,11 +6,11 @@ Key-Value Stores represent underlying storage components used in [Document Store
 
 ## Available Key-Value Stores
 
-- [SimpleKVStore](/docs/api/classes/SimpleKVStore): A simple Key-Value store with support of [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
-- [PostgresKVStore](/docs/api/classes/PostgresKVStore): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
+- [SimpleKVStore](/typescript/framework-api-reference/classes/simplekvstore/): A simple Key-Value store with support of [persisting](/typescript/framework/modules/data/stores#local-storage) data to disk.
+- [PostgresKVStore](/typescript/framework-api-reference/classes/postgreskvstore/): A PostgreSQL Key-Value store, see [PostgreSQL Storage](/typescript/framework/modules/data/stores#postgresql-storage).
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## API Reference
 
-- [BaseKVStore](/docs/api/classes/BaseKVStore)
+- [BaseKVStore](/typescript/framework-api-reference/classes/basekvstore/)

docs/src/content/docs/framework/modules/data/stores/vector_stores/index.mdx

@@ -8,14 +8,14 @@ Vector stores save embedding vectors of your ingested document chunks.
 
 Available Vector Stores are shown on the sidebar to the left. Additionally the following integrations exist without separate documentation:
 
-- [SimpleVectorStore](/docs/api/classes/SimpleVectorStore): A simple in-memory vector store with optional [persistance](/typescript/framework/modules/data/stores#local-storage) to disk.
-- [AstraDBVectorStore](/docs/api/classes/AstraDBVectorStore): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
-- [ChromaVectorStore](/docs/api/classes/ChromaVectorStore): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
-- [MilvusVectorStore](/docs/api/classes/MilvusVectorStore): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
-- [MongoDBAtlasVectorSearch](/docs/api/classes/MongoDBAtlasVectorSearch): A cloud-based vector search solution for MongoDB, see [mongodb.com](https://www.mongodb.com/products/platform/atlas-vector-search)
-- [PGVectorStore](/docs/api/classes/PGVectorStore): An open-source vector store built on PostgreSQL, see [pgvector Github](https://github.com/pgvector/pgvector)
-- [PineconeVectorStore](/docs/api/classes/PineconeVectorStore): A managed, cloud-native vector database, see [pinecone.io](https://www.pinecone.io/)
-- [WeaviateVectorStore](/docs/api/classes/WeaviateVectorStore): An open-source, ai-native vector database, see [weaviate.io](https://weaviate.io/)
+- [SimpleVectorStore](/typescript/framework-api-reference/classes/simplevectorstore/): A simple in-memory vector store with optional [persistance](/typescript/framework/modules/data/stores#local-storage) to disk.
+- [AstraDBVectorStore](/typescript/framework-api-reference/classes/astradbvectorstore/): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
+- [ChromaVectorStore](/typescript/framework-api-reference/classes/chromavectorstore/): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
+- [MilvusVectorStore](/typescript/framework-api-reference/classes/milvusvectorstore/): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
+- [MongoDBAtlasVectorSearch](/typescript/framework-api-reference/classes/mongodbatlasvectorsearch/): A cloud-based vector search solution for MongoDB, see [mongodb.com](https://www.mongodb.com/products/platform/atlas-vector-search)
+- [PGVectorStore](/typescript/framework-api-reference/classes/pgvectorstore/): An open-source vector store built on PostgreSQL, see [pgvector Github](https://github.com/pgvector/pgvector)
+- [PineconeVectorStore](/typescript/framework-api-reference/classes/pineconevectorstore/): A managed, cloud-native vector database, see [pinecone.io](https://www.pinecone.io/)
+- [WeaviateVectorStore](/typescript/framework-api-reference/classes/weaviatevectorstore/): An open-source, ai-native vector database, see [weaviate.io](https://weaviate.io/)
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 

docs/src/content/docs/framework/modules/data/stores/vector_stores/qdrant.mdx

@@ -99,4 +99,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [QdrantVectorStore](/docs/api/classes/QdrantVectorStore)
+- [QdrantVectorStore](/typescript/framework-api-reference/classes/qdrantvectorstore/)

docs/src/content/docs/framework/modules/data/stores/vector_stores/supabase.mdx

@@ -181,4 +181,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [SupabaseVectorStore](/docs/api/classes/SupabaseVectorStore)
+- [SupabaseVectorStore](/typescript/framework-api-reference/classes/supabasevectorstore/)

docs/src/content/docs/framework/modules/evaluation/correctness.mdx

@@ -62,4 +62,4 @@ the response is not correct with a score of 2.5
 
 ## API Reference
 
-- [CorrectnessEvaluator](/docs/api/classes/CorrectnessEvaluator)
+- [CorrectnessEvaluator](/typescript/framework-api-reference/classes/correctnessevaluator/)

docs/src/content/docs/framework/modules/evaluation/faithfulness.mdx

@@ -81,4 +81,4 @@ the response is faithful
 
 ## API Reference
 
-- [FaithfulnessEvaluator](/docs/api/classes/FaithfulnessEvaluator)
+- [FaithfulnessEvaluator](/typescript/framework-api-reference/classes/faithfulnessevaluator/)

docs/src/content/docs/framework/modules/evaluation/relevancy.mdx

@@ -75,4 +75,4 @@ the response is relevant
 
 ## API Reference
 
-- [RelevancyEvaluator](/docs/api/classes/RelevancyEvaluator)
+- [RelevancyEvaluator](/typescript/framework-api-reference/classes/relevancyevaluator/)

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

@@ -85,4 +85,4 @@ For questions or feedback, please contact us at [feedback@deepinfra.com](mailto:
 
 ## API Reference
 
-- [DeepInfraEmbedding](/docs/api/classes/DeepInfraEmbedding)
+- [DeepInfraEmbedding](/typescript/framework-api-reference/classes/deepinfraembedding/)

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

@@ -43,4 +43,4 @@ Settings.embedModel = new GeminiEmbedding({
 
 ## API Reference
 
-- [GeminiEmbedding](/docs/api/classes/GeminiEmbedding)
+- [GeminiEmbedding](/typescript/framework-api-reference/classes/geminiembedding/)

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

@@ -46,4 +46,4 @@ Settings.embedModel = new HuggingFaceEmbedding({
 
 ## API Reference
 
-- [HuggingFaceEmbedding](/docs/api/classes/HuggingFaceEmbedding)
+- [HuggingFaceEmbedding](/typescript/framework-api-reference/classes/huggingfaceembedding/)

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

@@ -55,11 +55,11 @@ Settings.embedModel = new OllamaEmbedding({
 Most available embeddings are listed in the sidebar on the left.
 Additionally the following integrations exist without separate documentation:
 
-- [ClipEmbedding](/docs/api/classes/ClipEmbedding) using `@xenova/transformers`
-- [FireworksEmbedding](/docs/api/classes/FireworksEmbedding) see [fireworks.ai](https://fireworks.ai/)
+- [ClipEmbedding](/typescript/framework-api-reference/classes/clipembedding/) using `@xenova/transformers`
+- [FireworksEmbedding](/typescript/framework-api-reference/classes/fireworksembedding/) see [fireworks.ai](https://fireworks.ai/)
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## API Reference
 
-- [OpenAIEmbedding](/docs/api/classes/OpenAIEmbedding)
+- [OpenAIEmbedding](/typescript/framework-api-reference/classes/openaiembedding/)

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

@@ -25,4 +25,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [JinaAIEmbedding](/docs/api/classes/JinaAIEmbedding)
+- [JinaAIEmbedding](/typescript/framework-api-reference/classes/jinaaiembedding/)

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

@@ -34,4 +34,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [MistralAIEmbedding](/docs/api/classes/MistralAIEmbedding)
+- [MistralAIEmbedding](/typescript/framework-api-reference/classes/mistralaiembedding/)

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

@@ -102,4 +102,4 @@ console.log(result); // Perfectly customized embeddings, ready to serve.
 
 ## API Reference
 
-- [MixedbreadAIEmbeddings](/docs/api/classes/MixedbreadAIEmbeddings)
+- [MixedbreadAIEmbeddings](/typescript/framework-api-reference/classes/mixedbreadaiembeddings/)

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

@@ -39,4 +39,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [OllamaEmbedding](/docs/api/classes/OllamaEmbedding)
+- [OllamaEmbedding](/typescript/framework-api-reference/classes/ollamaembedding/)

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

@@ -31,4 +31,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [OpenAIEmbedding](/docs/api/classes/OpenAIEmbedding)
+- [OpenAIEmbedding](/typescript/framework-api-reference/classes/openaiembedding/)

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/embeddings/together.mdx

@@ -27,4 +27,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [TogetherEmbedding](/docs/api/classes/TogetherEmbedding)
+- [TogetherEmbedding](/typescript/framework-api-reference/classes/togetherembedding/)

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

@@ -31,4 +31,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [VoyageAIEmbedding](/docs/api/classes/VoyageAIEmbedding)
+- [VoyageAIEmbedding](/typescript/framework-api-reference/classes/voyageaiembedding/)

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

@@ -76,4 +76,4 @@ async function main() {
 
 ## API Reference
 
-- [Anthropic](/docs/api/classes/Anthropic)
+- [Anthropic](/typescript/framework-api-reference/classes/anthropic/)

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

@@ -40,5 +40,5 @@ See the [Azure examples](https://github.com/run-llama/LlamaIndexTS/tree/main/exa
 
 ## API Reference
 
-- [AzureOpenAI](/docs/api/classes/AzureOpenAI)
-- [AzureOpenAIEmbedding](/docs/api/classes/AzureOpenAIEmbedding)
+- [AzureOpenAI](/typescript/framework-api-reference/classes/azureopenai/)
+- [AzureOpenAIEmbedding](/typescript/framework-api-reference/classes/azureopenaiembedding/)

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

@@ -96,4 +96,4 @@ If you have any feedback, please reach out to us at [feedback@deepinfra.com](mai
 
 ## API Reference
 
-- [DeepInfra](/docs/api/classes/DeepInfra)
+- [DeepInfra](/typescript/framework-api-reference/classes/deepinfra/)

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

@@ -53,4 +53,4 @@ Currently does not support function calling.
 
 ## API Reference
 
-- [DeepSeekLLM](/docs/api/classes/DeepSeekLLM)
+- [DeepSeekLLM](/typescript/framework-api-reference/classes/deepseekllm/)

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

@@ -65,4 +65,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [FireworksLLM](/docs/api/classes/FireworksLLM)
+- [FireworksLLM](/typescript/framework-api-reference/classes/fireworksllm/)

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

@@ -192,4 +192,4 @@ async function main() {
 
 ## API Reference
 
-- [Gemini](/docs/api/classes/Gemini)
+- [Gemini](/typescript/framework-api-reference/classes/gemini/)

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

@@ -59,4 +59,4 @@ const results = await queryEngine.query({
 
 ## API Reference
 
-- [Groq](/docs/api/classes/Groq)
+- [Groq](/typescript/framework-api-reference/classes/groq/)

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

@@ -39,11 +39,11 @@ For local LLMs, currently we recommend the use of [Ollama](/typescript/framework
 
 Most available LLMs are listed in the sidebar on the left. Additionally the following integrations exist without separate documentation:
 
-- [HuggingFaceLLM](/docs/api/classes/HuggingFaceLLM) and [HuggingFaceInferenceAPI](/docs/api/classes/HuggingFaceInferenceAPI).
-- [ReplicateLLM](/docs/api/classes/ReplicateLLM) see [replicate.com](https://replicate.com/)
+- [HuggingFaceLLM](/typescript/framework-api-reference/classes/huggingfacellm/) and [HuggingFaceInferenceAPI](/typescript/framework-api-reference/classes/huggingfaceinferenceapi/).
+- [ReplicateLLM](/typescript/framework-api-reference/classes/replicatellm/) see [replicate.com](https://replicate.com/)
 
 Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
 
 ## API Reference
 
-- [OpenAI](/docs/api/classes/OpenAI)
+- [OpenAI](/typescript/framework-api-reference/classes/openai/)

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

@@ -81,4 +81,4 @@ async function main() {
 
 ## API Reference
 
-- [MistralAI](/docs/api/classes/MistralAI)
+- [MistralAI](/typescript/framework-api-reference/classes/mistralai/)

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

@@ -115,4 +115,4 @@ async function main() {
 
 ## API Reference
 
-- [Ollama](/docs/api/classes/Ollama)
+- [Ollama](/typescript/framework-api-reference/classes/ollama/)

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

@@ -377,7 +377,7 @@ async function main() {
 
 ## API Reference
 
-- [OpenAI](/docs/api/classes/OpenAI)
+- [OpenAI](/typescript/framework-api-reference/classes/openai/)
 
 
 # OpenAI Live LLM

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/)
+

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

@@ -119,4 +119,4 @@ Currently does not support function calling.
 
 ## API Reference
 
-- [Perplexity](/docs/api/classes/Perplexity)
+- [Perplexity](/typescript/framework-api-reference/classes/perplexity/)

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

@@ -83,4 +83,4 @@ async function main() {
 
 ## API Reference
 
-- [Portkey](/docs/api/classes/Portkey)
+- [Portkey](/typescript/framework-api-reference/classes/portkey/)

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

@@ -81,4 +81,4 @@ async function main() {
 
 ## API Reference
 
-- [TogetherLLM](/docs/api/classes/TogetherLLM)
+- [TogetherLLM](/typescript/framework-api-reference/classes/togetherllm/)

docs/src/content/docs/framework/modules/models/prompt/index.mdx

@@ -83,4 +83,4 @@ const response = await queryEngine.query({
 ## API Reference
 
 - [Response Synthesizer](/typescript/framework/modules/rag/response_synthesizer)
-- [CompactAndRefine](/docs/api/classes/CompactAndRefine)
+- [CompactAndRefine](/typescript/framework-api-reference/classes/compactandrefine/)

docs/src/content/docs/framework/modules/rag/chat_engine.mdx

@@ -40,6 +40,6 @@ for await (const chunk of stream) {
 
 ## Api References
 
-- [ContextChatEngine](/docs/api/classes/ContextChatEngine)
-- [CondenseQuestionChatEngine](/docs/api/classes/CondenseQuestionChatEngine)
-- [SimpleChatEngine](/docs/api/classes/SimpleChatEngine)
+- [ContextChatEngine](/typescript/framework-api-reference/classes/contextchatengine/)
+- [CondenseQuestionChatEngine](/typescript/framework-api-reference/classes/condensequestionchatengine/)
+- [SimpleChatEngine](/typescript/framework-api-reference/classes/simplechatengine/)

docs/src/content/docs/framework/modules/rag/node_postprocessors/cohere_reranker.mdx

@@ -67,4 +67,4 @@ const response = await queryEngine.query("Where did the author grown up?");
 
 ## API Reference
 
-- [CohereRerank](/docs/api/classes/CohereRerank)
+- [CohereRerank](/typescript/framework-api-reference/classes/coherererank/)

docs/src/content/docs/framework/modules/rag/node_postprocessors/index.mdx

@@ -112,5 +112,5 @@ const filteredNodes = processor.postprocessNodes(nodes);
 
 ## API Reference
 
-- [SimilarityPostprocessor](/docs/api/classes/SimilarityPostprocessor)
-- [MetadataReplacementPostProcessor](/docs/api/classes/MetadataReplacementPostProcessor)
+- [SimilarityPostprocessor](/typescript/framework-api-reference/classes/similaritypostprocessor/)
+- [MetadataReplacementPostProcessor](/typescript/framework-api-reference/classes/metadatareplacementpostprocessor/)

docs/src/content/docs/framework/modules/rag/node_postprocessors/jinaai_reranker.mdx

@@ -70,4 +70,4 @@ const response = await queryEngine.query("Where did the author grown up?");
 
 ## API Reference
 
-- [JinaAIReranker](/docs/api/classes/JinaAIReranker)
+- [JinaAIReranker](/typescript/framework-api-reference/classes/jinaaireranker/)

docs/src/content/docs/framework/modules/rag/node_postprocessors/mixedbreadiai_reranker.mdx

@@ -168,4 +168,4 @@ console.log(result); // Perfectly customized results, ready to serve.
 
 ## API Reference
 
-- [MixedbreadAIReranker](/docs/api/classes/MixedbreadAIReranker)
+- [MixedbreadAIReranker](/typescript/framework-api-reference/classes/mixedbreadaireranker/)

docs/src/content/docs/framework/modules/rag/query_engines/index.mdx

@@ -38,6 +38,6 @@ You can learn more about Tools by taking a look at the LlamaIndex Python documen
 
 ## API Reference
 
-- [RetrieverQueryEngine](/docs/api/classes/RetrieverQueryEngine)
-- [SubQuestionQueryEngine](/docs/api/classes/SubQuestionQueryEngine)
-- [QueryEngineTool](/docs/api/classes/QueryEngineTool)
+- [RetrieverQueryEngine](/typescript/framework-api-reference/classes/retrieverqueryengine/)
+- [SubQuestionQueryEngine](/typescript/framework-api-reference/classes/subquestionqueryengine/)
+- [QueryEngineTool](/typescript/framework-api-reference/classes/queryenginetool/)

docs/src/content/docs/framework/modules/rag/query_engines/metadata_filtering.mdx

@@ -150,6 +150,6 @@ main();
 
 ## API Reference
 
-- [VectorStoreIndex](/docs/api/classes/VectorStoreIndex)
-- [ChromaVectorStore](/docs/api/classes/ChromaVectorStore)
+- [VectorStoreIndex](/typescript/framework-api-reference/classes/vectorstoreindex/)
+- [ChromaVectorStore](/typescript/framework-api-reference/classes/chromavectorstore/)
 - [MetadataFilter](/docs/api/interfaces/MetadataFilter)

docs/src/content/docs/framework/modules/rag/query_engines/router_query_engine.mdx

@@ -172,4 +172,4 @@ main().then(() => console.log("Done"));
 
 ## API Reference
 
-- [RouterQueryEngine](/docs/api/classes/RouterQueryEngine)
+- [RouterQueryEngine](/typescript/framework-api-reference/classes/routerqueryengine/)

docs/src/content/docs/framework/modules/rag/response_synthesizer.mdx

@@ -59,7 +59,7 @@ for await (const chunk of stream) {
 
 - [getResponseSynthesizer](/docs/api/functions/getResponseSynthesizer)
 - [responseModeSchema](/docs/api/variables/responseModeSchema)
-- [Refine](/docs/api/classes/Refine)
-- [CompactAndRefine](/docs/api/classes/CompactAndRefine)
-- [TreeSummarize](/docs/api/classes/TreeSummarize)
-- [MultiModal](/docs/api/classes/MultiModal)
+- [Refine](/typescript/framework-api-reference/classes/refine/)
+- [CompactAndRefine](/typescript/framework-api-reference/classes/compactandrefine/)
+- [TreeSummarize](/typescript/framework-api-reference/classes/treesummarize/)
+- [MultiModal](/typescript/framework-api-reference/classes/multimodal/)

docs/src/content/docs/framework/modules/rag/retriever.mdx

@@ -4,13 +4,13 @@ title: Retriever
 
 A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string.
 
-- [VectorIndexRetriever](/docs/api/classes/VectorIndexRetriever) will fetch the top-k most similar nodes. Ideal for dense retrieval to find most relevant nodes.
-- [SummaryIndexRetriever](/docs/api/classes/SummaryIndexRetriever) will fetch all nodes no matter the query. Ideal when complete context is necessary, e.g. analyzing large datasets.
-- [SummaryIndexLLMRetriever](/docs/api/classes/SummaryIndexLLMRetriever) utilizes an LLM to score and filter nodes based on relevancy to the query.
-- [KeywordTableLLMRetriever](/docs/api/classes/KeywordTableLLMRetriever) uses an LLM to extract keywords from the query and retrieve relevant nodes based on keyword matches.
-- [KeywordTableSimpleRetriever](/docs/api/classes/KeywordTableSimpleRetriever) uses a basic frequency-based approach to extract keywords and retrieve nodes.
-- [KeywordTableRAKERetriever](/docs/api/classes/KeywordTableRAKERetriever) uses the RAKE (Rapid Automatic Keyword Extraction) algorithm to extract keywords from the query, focusing on co-occurrence and context for keyword-based retrieval.
-- [Bm25Retriever](/docs/api/classes/Bm25Retriever) uses the BM25 algorithm to extract keywords from the query and retrieve relevant nodes based on keyword matches.
+- [VectorIndexRetriever](/typescript/framework-api-reference/classes/vectorindexretriever/) will fetch the top-k most similar nodes. Ideal for dense retrieval to find most relevant nodes.
+- [SummaryIndexRetriever](/typescript/framework-api-reference/classes/summaryindexretriever/) will fetch all nodes no matter the query. Ideal when complete context is necessary, e.g. analyzing large datasets.
+- [SummaryIndexLLMRetriever](/typescript/framework-api-reference/classes/summaryindexllmretriever/) utilizes an LLM to score and filter nodes based on relevancy to the query.
+- [KeywordTableLLMRetriever](/typescript/framework-api-reference/classes/keywordtablellmretriever/) uses an LLM to extract keywords from the query and retrieve relevant nodes based on keyword matches.
+- [KeywordTableSimpleRetriever](/typescript/framework-api-reference/classes/keywordtablesimpleretriever/) uses a basic frequency-based approach to extract keywords and retrieve nodes.
+- [KeywordTableRAKERetriever](/typescript/framework-api-reference/classes/keywordtablerakeretriever/) uses the RAKE (Rapid Automatic Keyword Extraction) algorithm to extract keywords from the query, focusing on co-occurrence and context for keyword-based retrieval.
+- [Bm25Retriever](/typescript/framework-api-reference/classes/bm25retriever/) uses the BM25 algorithm to extract keywords from the query and retrieve relevant nodes based on keyword matches.
 
 ```typescript
 const retriever = vectorIndex.asRetriever({

docs/src/content/docs/framework/modules/ui/llamaindex-server.mdx

@@ -5,7 +5,7 @@ description: Running LlamaIndex workflows with both API endpoints and a user int
 
 # LlamaIndex Server
 
-LlamaIndexServer is a Next.js-based application that allows you to quickly launch your [LlamaIndex Workflows](https://ts.llamaindex.ai/typescript/framework/modules/agents/workflows) and [Agent Workflows](https://ts.llamaindex.ai/typescript/framework/modules/agents/agent_workflow) as an API server with an optional chat UI. It provides a complete environment for running LlamaIndex workflows with both API endpoints and a user interface for interaction.
+LlamaIndexServer is a Next.js-based application that allows you to quickly launch your [LlamaIndex Workflows](/typescript/workflows/) as an API server with an optional chat UI. It provides a complete environment for running LlamaIndex workflows with both API endpoints and a user interface for interaction.
 
 ## Features
 

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 +1,19 @@
 # @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
+
+- @llamaindex/huggingface@0.1.31
+
 ## 0.1.62
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.62",
+  "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",
@@ -17,7 +17,7 @@
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
     "typescript": "^5.8.3",
-    "vite": "^6.3.6"
+    "vite": "^6.4.1"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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 +1,62 @@
 # 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
+
+- Updated dependencies [1028877]
+  - @llamaindex/openai@0.4.21
+  - @llamaindex/clip@0.0.77
+  - @llamaindex/deepinfra@0.0.77
+  - @llamaindex/deepseek@0.0.39
+  - @llamaindex/fireworks@0.0.37
+  - @llamaindex/groq@0.0.93
+  - @llamaindex/huggingface@0.1.31
+  - @llamaindex/jinaai@0.0.37
+  - @llamaindex/perplexity@0.0.34
+  - @llamaindex/azure@0.1.38
+  - @llamaindex/together@0.0.37
+  - @llamaindex/vllm@0.0.63
+  - @llamaindex/xai@0.0.24
+
 ## 0.3.42
 
 ### 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/openai/live/browser/open-ai-realtime/package.json

@@ -24,6 +24,6 @@
     "globals": "^16.0.0",
     "typescript": "~5.8.3",
     "typescript-eslint": "^8.36.0",
-    "vite": "^6.3.5"
+    "vite": "^6.4.1"
   }
 }

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": "0.3.42",
+  "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": "^0.1.37",
+    "@llamaindex/azure": "^0.2.0",
     "@llamaindex/bm25-retriever": "^0.0.11",
     "@llamaindex/chroma": "^0.0.36",
-    "@llamaindex/clip": "^0.0.76",
-    "llama-cloud-services": "^0.3.5",
+    "@llamaindex/clip": "^0.0.78",
     "@llamaindex/cohere": "^0.0.36",
     "@llamaindex/core": "^0.6.22",
-    "@llamaindex/deepinfra": "^0.0.76",
-    "@llamaindex/deepseek": "^0.0.38",
+    "@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": "^0.0.36",
-    "@llamaindex/google": "^0.3.22",
-    "@llamaindex/groq": "^0.0.92",
-    "@llamaindex/huggingface": "^0.1.30",
-    "@llamaindex/jinaai": "^0.0.36",
+    "@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": "^0.4.20",
-    "@llamaindex/perplexity": "^0.0.33",
+    "@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": "^0.0.36",
-    "@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": "^0.0.62",
+    "@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": "^0.0.23",
+    "@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 +1,19 @@
 # @llamaindex/core-test
 
+## 0.1.23
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
+## 0.1.22
+
+### Patch Changes
+
+- Updated dependencies [1028877]
+  - @llamaindex/openai@0.4.21
+
 ## 0.1.21
 
 ### Patch Changes

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.21",
+  "version": "0.1.23",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/providers/aws/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/community
 
+## 0.0.120
+
+### Patch Changes
+
+- dea763e: fix typo for APAC Claude Sonnet 4 model name
+
 ## 0.0.119
 
 ### Patch Changes

packages/providers/aws/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/aws",
   "description": "AWS package for LlamaIndexTS",
-  "version": "0.0.119",
+  "version": "0.0.120",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/providers/aws/src/llm/bedrock/index.ts

@@ -149,7 +149,7 @@ export const INFERENCE_BEDROCK_MODELS = {
   APAC_ANTHROPIC_CLAUDE_3_7_SONNET:
     "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
   APAC_ANTHROPIC_CLAUDE_4_SONNET:
-    "apac.anthropic.claude-sonnet-4-20250514-v1:0q",
+    "apac.anthropic.claude-sonnet-4-20250514-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_HAIKU: "apac.anthropic.claude-3-haiku-20240307-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_SONNET:
     "apac.anthropic.claude-3-sonnet-20240229-v1:0",

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/clip
 
+## 0.0.78
+
+### Patch Changes
+
+- Updated dependencies [76709c2]
+  - @llamaindex/openai@0.4.22
+
+## 0.0.77
+
+### Patch Changes
+
+- Updated dependencies [1028877]
+  - @llamaindex/openai@0.4.21
+
 ## 0.0.76
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.76",
+  "version": "0.0.78",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",