changeset

.changeset/many-groups-take.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/doc": patch
+---
+
+Minor updates in deployment docs

apps/next/CHANGELOG.md

@@ -1,25 +1,5 @@
 # @llamaindex/doc
 
-## 0.2.44
-
-### Patch Changes
-
-- 38da40b: feat: VectoryMemoryBlock
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/cloud@4.0.26
-  - llamaindex@0.11.21
-  - @llamaindex/node-parser@2.0.17
-  - @llamaindex/openai@0.4.12
-  - @llamaindex/readers@3.1.16
-  - @llamaindex/workflow@1.1.17
-
-## 0.2.43
-
-### Patch Changes
-
-- ea15e75: Minor updates in deployment docs
-
 ## 0.2.42
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.44",
+  "version": "0.2.42",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",

apps/next/src/content/docs/llamaindex/modules/data/memory/index.mdx

@@ -106,40 +106,34 @@ const memory = createMemory({
 
 Long-term memory is represented as `Memory Block` objects. These objects contain information that are from previous user sessions or from the beginning of the current conversation. When memory is retrieved (by calling `getLLM`), the short-term and long-term memories are merged together within the given `tokenLimit`. 
 
-Currently, there are three predefined memory blocks:
+Currently, there are two predefined memory blocks:
 
 - `staticBlock`: A memory block that stores a static piece of information.
 - `factExtractionBlock`: A memory block that extracts facts from the chat history.
-- `vectorBlock`: A memory block that stores and retrieves chat messages from a vector database using semantic similarity search. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
 
 This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
 
 ```ts
-import { createMemory, factExtractionBlock, staticBlock, vectorBlock } from "llamaindex";
-import { QdrantVectorStore } from "@llamaindex/qdrant";
-import { OpenAIEmbedding } from "@llamaindex/openai";
+import { createMemory, factExtractionBlock, staticBlock } from "llamaindex";
 
 const memoryBlocks= [
   staticBlock({
+    id: "core_info",
     content: "My name is Logan, and I live in Saskatoon. I work at LlamaIndex.",
   }),
   factExtractionBlock({
+    id: "user-extracted_info",
     priority: 1,
     llm: llm,
     maxFacts: 50,
   }),
-  vectorBlock({
-    vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
-    priority: 2,
-  }),
 ];
 ```
 
-Here, we've setup three memory blocks:
+Here, we've setup two memory blocks:
 
-- `staticBlock`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
-- `factExtractionBlock`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
-- `vectorBlock`: A vector memory block that will store in a vector database and retrieve them from there. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
+- `core_info`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
+- `extracted_info`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
 
 You'll also notice that we've set the `priority` for the `factExtractionBlock` block. This is used to determine the handling when the memory blocks content (i.e. long-term memory) + short-term memory exceeds the token limit on the `Memory` object.
 
@@ -164,46 +158,6 @@ When memory is retrieved (using `getLLM`), the short-term and long-term memories
 
 The amount of short-term memory included is specified by the `shortTermTokenLimitRatio`. If it's set to `0.7`, 70% of the `tokenLimit` is used for short-term memory (not including the static memory block).
 
-
-#### VectorBlock Configuration Options
-
-The `vectorBlock` offers several configuration options to customize its behavior:
-
-```ts
-vectorBlock({
-  vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
-  priority: 2,
-  retrievalContextWindow: 5, // Number of recent messages to use for context when retrieving
-  formatTemplate: new PromptTemplate({ template: "Context: {{ context }}" }), // Custom formatting template
-  nodePostprocessors: [/* custom postprocessors */], // Apply processing to retrieved nodes
-  queryOptions: {
-    similarityTopK: 3, // Number of top similar results to return (default: 2)
-    mode: VectorStoreQueryMode.DEFAULT, // Query mode for the vector store
-    sessionFilterKey: "session_id", // Metadata key for session filtering (default: "session_id")
-    // Custom filters can be added here - session filter is automatically included
-    filters: {
-      filters: [
-        { key: "custom_field", value: "custom_value", operator: "==" }
-      ],
-      condition: "and"
-    }
-  }
-})
-```
-
-**Key Configuration Options:**
-
-- **`retrievalContextWindow`**: Number of recent messages to consider when creating the retrieval query (default: 5). A larger window provides more context but may be less precise.
-- **`formatTemplate`**: Template for formatting retrieved information before adding to memory. Defaults to a simple context template.
-- **`nodePostprocessors`**: Array of postprocessors to apply to retrieved nodes, useful for filtering or transforming results.
-- **`queryOptions.similarityTopK`**: Number of most similar messages to retrieve from the vector store (default: 2).
-- **`queryOptions.sessionFilterKey`**: Metadata key used to isolate memory between different sessions (default: "session_id").
-- **`queryOptions.filters`**: Additional metadata filters for retrieval. The session filter is automatically added to ensure memory isolation.
-
-**Session Isolation:**
-
-The vectorBlock automatically adds a session filter using the block's ID to ensure that memories from different sessions don't interfere with each other. This filter uses the `sessionFilterKey` (default: "session_id") and can be customized if needed.
-
 ## Persistence with Snapshots
 
 Save and restore memory state:

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

@@ -1,11 +1,5 @@
 # @llamaindex/cloudflare-worker-agent-test
 
-## 0.0.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.0.181
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.182",
+  "version": "0.0.181",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/llama-parse-browser/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/llama-parse-browser-test
 
-## 0.0.81
-
-### Patch Changes
-
-- @llamaindex/cloud@4.0.26
-
 ## 0.0.80
 
 ### Patch Changes

e2e/examples/llama-parse-browser/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.81",
+  "version": "0.0.80",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/next-agent-test
 
-## 0.1.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.1.181
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.182",
+  "version": "0.1.181",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,11 +1,5 @@
 # test-edge-runtime
 
-## 0.1.181
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.1.180
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.181",
+  "version": "0.1.180",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,13 +1,5 @@
 # @llamaindex/next-node-runtime
 
-## 0.1.51
-
-### Patch Changes
-
-- llamaindex@0.11.21
-- @llamaindex/huggingface@0.1.22
-- @llamaindex/readers@3.1.16
-
 ## 0.1.50
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.51",
+  "version": "0.1.50",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,11 +1,5 @@
 # vite-import-llamaindex
 
-## 0.0.48
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.0.47
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.48",
+  "version": "0.0.47",
   "type": "module",
   "scripts": {
     "build": "vite build",

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

@@ -1,11 +1,5 @@
 # @llamaindex/waku-query-engine-test
 
-## 0.0.182
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.0.181
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.182",
+  "version": "0.0.181",
   "type": "module",
   "private": true,
   "scripts": {

e2e/node/vector-store/pinecone.e2e.ts

@@ -23,7 +23,7 @@ await test("pinecone", async (t) => {
   });
 
   const vectorStore = new PineconeVectorStore({
-    embedModel: openaiEmbedding,
+    embeddingModel: openaiEmbedding,
   });
 
   t.after(async () => {

examples/CHANGELOG.md

@@ -1,57 +1,5 @@
 # examples
 
-## 0.3.33
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/cloud@4.0.26
-  - llamaindex@0.11.21
-  - @llamaindex/node-parser@2.0.17
-  - @llamaindex/anthropic@0.3.19
-  - @llamaindex/assemblyai@0.1.16
-  - @llamaindex/clip@0.0.68
-  - @llamaindex/cohere@0.0.31
-  - @llamaindex/deepinfra@0.0.68
-  - @llamaindex/discord@0.1.16
-  - @llamaindex/google@0.3.16
-  - @llamaindex/huggingface@0.1.22
-  - @llamaindex/jinaai@0.0.28
-  - @llamaindex/mistral@0.1.17
-  - @llamaindex/mixedbread@0.0.31
-  - @llamaindex/notion@0.1.16
-  - @llamaindex/ollama@0.1.17
-  - @llamaindex/openai@0.4.12
-  - @llamaindex/perplexity@0.0.25
-  - @llamaindex/portkey-ai@0.0.59
-  - @llamaindex/replicate@0.0.59
-  - @llamaindex/bm25-retriever@0.0.6
-  - @llamaindex/astra@0.0.31
-  - @llamaindex/azure@0.1.29
-  - @llamaindex/chroma@0.0.31
-  - @llamaindex/elastic-search@0.1.17
-  - @llamaindex/firestore@1.0.24
-  - @llamaindex/milvus@0.1.26
-  - @llamaindex/mongodb@0.0.32
-  - @llamaindex/pinecone@0.1.17
-  - @llamaindex/postgres@0.0.60
-  - @llamaindex/qdrant@0.1.27
-  - @llamaindex/supabase@0.1.18
-  - @llamaindex/upstash@0.0.31
-  - @llamaindex/weaviate@0.0.32
-  - @llamaindex/vercel@0.1.17
-  - @llamaindex/voyage-ai@1.0.23
-  - @llamaindex/readers@3.1.16
-  - @llamaindex/tools@0.1.7
-  - @llamaindex/workflow@1.1.17
-  - @llamaindex/deepseek@0.0.29
-  - @llamaindex/fireworks@0.0.28
-  - @llamaindex/groq@0.0.84
-  - @llamaindex/together@0.0.28
-  - @llamaindex/vllm@0.0.54
-  - @llamaindex/xai@0.0.15
-
 ## 0.3.32
 
 ### Patch Changes

examples/agents/memory/vector-block.ts

@@ -1,150 +0,0 @@
-/**
- * Example: Vector Memory Block
- *
- * This example demonstrates how to use the VectorMemoryBlock to store and retrieve
- * conversation history using vector similarity search. The vector memory block
- * stores messages in a vector store and can retrieve relevant context based on
- * semantic similarity to recent messages.
- */
-
-import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
-import { QdrantVectorStore } from "@llamaindex/qdrant";
-import { createMemory, vectorBlock } from "llamaindex";
-
-// Set up the LLM and embedding model
-const llm = new OpenAI({ model: "gpt-4.1-mini" });
-const embedModel = new OpenAIEmbedding({ model: "text-embedding-3-small" });
-
-// Simulate a conversation with some context
-// This conversation has 8 messages, which is more than the token limit of 100 tokens (set below)
-// The last 4 messages are kept in to short term memory block (as their tokens are in the limit)
-// Whereas the first 5 messages are added to long term memory block (in here we will use the vector memory block with Qdrant)
-const CONVERSATION_TURNS = [
-  //// This is the first 5 messages that are added to long term memory block (vector memory block)
-  {
-    role: "user",
-    content: "Hi, I'm Sarah and I work as a data scientist at Google.",
-  },
-  {
-    role: "assistant",
-    content:
-      "Hello Sarah! It's great to meet you. Data science at Google must be exciting!",
-  },
-  {
-    role: "user",
-    content:
-      "Yes, I specialize in machine learning and natural language processing.",
-  },
-  {
-    role: "assistant",
-    content: "That's impressive! ML and NLP are fascinating fields.",
-  },
-  {
-    role: "user",
-    content:
-      "I have a PhD in Computer Science from Stanford, and I love hiking on weekends.",
-  },
-
-  //// This is the last 4 messages that are added to short term memory block
-  {
-    role: "assistant",
-    content:
-      "Wow, Stanford PhD! And hiking is a great way to unwind from tech work.",
-  },
-  {
-    role: "user",
-    content: "I also have two cats named Whiskers and Mittens.",
-  },
-  {
-    role: "assistant",
-    content:
-      "Cats make wonderful companions! Whiskers and Mittens are cute names.",
-  },
-  {
-    role: "user",
-    content: "Summary information about Sarah and her cats",
-  },
-];
-
-async function main() {
-  console.log("=== Vector Memory Block Example ===\n");
-
-  /**
-   * Create a vector store. You can quickly get a local instance of Qdrant running with Docker:
-   * ```bash
-   * docker pull qdrant/qdrant
-   * docker run -p 6333:6333 qdrant/qdrant
-   * ```
-   *
-   * Go to http://localhost:6333/dashboard#/collections to see your data
-   */
-  const vectorStore = new QdrantVectorStore({
-    url: "http://localhost:6333",
-    embedModel,
-  });
-
-  // Create a vector memory block using the factory function
-  const vectorMemoryBlock = vectorBlock({
-    vectorStore,
-    priority: 5,
-  });
-
-  // Create a memory store with the vector memory block
-  const memory = createMemory([], {
-    llm,
-    memoryBlocks: [vectorMemoryBlock],
-    tokenLimit: 100,
-    shortTermTokenLimitRatio: 0.7,
-  });
-
-  // Store the conversation history in the vector memory
-  console.log(`Adding ${CONVERSATION_TURNS.length} messages to the memory...`);
-  for (const message of CONVERSATION_TURNS) {
-    await memory.add(message);
-  }
-
-  // Retrieve relevant context for the current user request
-  console.log("Retrieving relevant context...");
-  const chatHistory = await memory.getLLM();
-
-  // You will see there's 1 generated context message from vector memory block, and 4 messages from short term memory block
-  console.log("Chat memory:", chatHistory);
-
-  // Now simulate the assistant responding with context
-  console.log("\nAssistant response with context:");
-  const response = await llm.chat({
-    messages: chatHistory,
-  });
-  console.log(response.message.content);
-
-  // Try adding more messages to the memory
-  const newMessages = [
-    {
-      role: "user",
-      content: "Write a long paragraph about weather in Tokyo",
-    },
-    {
-      role: "assistant",
-      content:
-        "The weather in Tokyo is sunny and warm. The temperature is around 20 degrees Celsius. The weather is very nice and the people are friendly.",
-    },
-    {
-      role: "user",
-      content: "What is the weather in Tokyo?",
-    },
-  ];
-  // Add the new messages to the memory
-  for (const message of newMessages) {
-    await memory.add(message);
-  }
-
-  // Try retrieving the new messages
-  const newChatHistory = await memory.getLLM();
-  // You can see now that new chat history will contain the nodes (separated by `\n`) in the
-  // context message that is generated by the vector memory block
-  // The number of retrieved nodes is set by `similarityTopK` in `queryOptions` of `vectorBlock`
-  // (default `similarityTopK` is 2)
-  console.log("New chat history:", newChatHistory);
-}
-
-main().catch(console.error);

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.33",
+  "version": "0.3.32",
   "private": true,
   "scripts": {
     "lint": "eslint .",
@@ -11,52 +11,52 @@
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.19",
-    "@llamaindex/assemblyai": "^0.1.16",
-    "@llamaindex/astra": "^0.0.31",
-    "@llamaindex/azure": "^0.1.29",
-    "@llamaindex/bm25-retriever": "^0.0.6",
-    "@llamaindex/chroma": "^0.0.31",
-    "@llamaindex/clip": "^0.0.68",
-    "@llamaindex/cloud": "^4.0.26",
-    "@llamaindex/cohere": "^0.0.31",
-    "@llamaindex/core": "^0.6.17",
-    "@llamaindex/deepinfra": "^0.0.68",
-    "@llamaindex/deepseek": "^0.0.29",
-    "@llamaindex/discord": "^0.1.16",
-    "@llamaindex/elastic-search": "^0.1.17",
+    "@llamaindex/anthropic": "^0.3.18",
+    "@llamaindex/assemblyai": "^0.1.15",
+    "@llamaindex/astra": "^0.0.30",
+    "@llamaindex/azure": "^0.1.28",
+    "@llamaindex/bm25-retriever": "^0.0.5",
+    "@llamaindex/chroma": "^0.0.30",
+    "@llamaindex/clip": "^0.0.67",
+    "@llamaindex/cloud": "^4.0.25",
+    "@llamaindex/cohere": "^0.0.30",
+    "@llamaindex/core": "^0.6.16",
+    "@llamaindex/deepinfra": "^0.0.67",
+    "@llamaindex/deepseek": "^0.0.28",
+    "@llamaindex/discord": "^0.1.15",
+    "@llamaindex/elastic-search": "^0.1.16",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.24",
-    "@llamaindex/fireworks": "^0.0.28",
-    "@llamaindex/google": "^0.3.16",
-    "@llamaindex/groq": "^0.0.84",
-    "@llamaindex/huggingface": "^0.1.22",
-    "@llamaindex/jinaai": "^0.0.28",
-    "@llamaindex/milvus": "^0.1.26",
-    "@llamaindex/mistral": "^0.1.17",
-    "@llamaindex/mixedbread": "^0.0.31",
-    "@llamaindex/mongodb": "^0.0.32",
-    "@llamaindex/node-parser": "^2.0.17",
-    "@llamaindex/notion": "^0.1.16",
-    "@llamaindex/ollama": "^0.1.17",
-    "@llamaindex/openai": "^0.4.12",
-    "@llamaindex/perplexity": "^0.0.25",
-    "@llamaindex/pinecone": "^0.1.17",
-    "@llamaindex/portkey-ai": "^0.0.59",
-    "@llamaindex/postgres": "^0.0.60",
-    "@llamaindex/qdrant": "^0.1.27",
-    "@llamaindex/readers": "^3.1.16",
-    "@llamaindex/replicate": "^0.0.59",
-    "@llamaindex/supabase": "^0.1.18",
-    "@llamaindex/together": "^0.0.28",
-    "@llamaindex/tools": "^0.1.7",
-    "@llamaindex/upstash": "^0.0.31",
-    "@llamaindex/vercel": "^0.1.17",
-    "@llamaindex/vllm": "^0.0.54",
-    "@llamaindex/voyage-ai": "^1.0.23",
-    "@llamaindex/weaviate": "^0.0.32",
-    "@llamaindex/workflow": "^1.1.17",
-    "@llamaindex/xai": "^0.0.15",
+    "@llamaindex/firestore": "^1.0.23",
+    "@llamaindex/fireworks": "^0.0.27",
+    "@llamaindex/google": "^0.3.15",
+    "@llamaindex/groq": "^0.0.83",
+    "@llamaindex/huggingface": "^0.1.21",
+    "@llamaindex/jinaai": "^0.0.27",
+    "@llamaindex/milvus": "^0.1.25",
+    "@llamaindex/mistral": "^0.1.16",
+    "@llamaindex/mixedbread": "^0.0.30",
+    "@llamaindex/mongodb": "^0.0.31",
+    "@llamaindex/node-parser": "^2.0.16",
+    "@llamaindex/notion": "^0.1.15",
+    "@llamaindex/ollama": "^0.1.16",
+    "@llamaindex/openai": "^0.4.11",
+    "@llamaindex/perplexity": "^0.0.24",
+    "@llamaindex/pinecone": "^0.1.16",
+    "@llamaindex/portkey-ai": "^0.0.58",
+    "@llamaindex/postgres": "^0.0.59",
+    "@llamaindex/qdrant": "^0.1.26",
+    "@llamaindex/readers": "^3.1.15",
+    "@llamaindex/replicate": "^0.0.58",
+    "@llamaindex/supabase": "^0.1.17",
+    "@llamaindex/together": "^0.0.27",
+    "@llamaindex/tools": "^0.1.6",
+    "@llamaindex/upstash": "^0.0.30",
+    "@llamaindex/vercel": "^0.1.16",
+    "@llamaindex/vllm": "^0.0.53",
+    "@llamaindex/voyage-ai": "^1.0.22",
+    "@llamaindex/weaviate": "^0.0.31",
+    "@llamaindex/workflow": "^1.1.16",
+    "@llamaindex/xai": "^0.0.14",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
@@ -65,7 +65,7 @@
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.21",
+    "llamaindex": "^0.11.20",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",

examples/storage/qdrantdb/with-gemini.ts

@@ -15,7 +15,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embedModel: embedding,
+    embeddingModel: embedding,
     collectionName: "gemini_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

examples/storage/qdrantdb/with-jina.ts

@@ -16,7 +16,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embedModel: embedding,
+    embeddingModel: embedding,
     collectionName: "jina_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

packages/autotool/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/autotool
 
-## 8.0.21
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 8.0.20
 
 ### Patch Changes

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

@@ -1,12 +1,5 @@
 # @llamaindex/autotool-01-node-example
 
-## 0.0.129
-
-### Patch Changes
-
-- llamaindex@0.11.21
-- @llamaindex/autotool@8.0.21
-
 ## 0.0.128
 
 ### 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": "0.0.129"
+  "version": "0.0.128"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.21",
+  "version": "8.0.20",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/cloud
 
-## 4.0.26
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 4.0.25
 
 ### Patch Changes

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "4.0.26",
+  "version": "4.0.25",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/core/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/core
 
-## 0.6.17
-
-### Patch Changes
-
-- 38da40b: feat: VectoryMemoryBlock
-
 ## 0.6.16
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.6.17",
+  "version": "0.6.16",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/memory/block/base.ts

@@ -39,9 +39,7 @@ export abstract class BaseMemoryBlock<
    *
    * @returns The memory block content as an array of ChatMessage.
    */
-  abstract get(
-    messages?: MemoryMessage<TAdditionalMessageOptions>[],
-  ): Promise<MemoryMessage<TAdditionalMessageOptions>[]>;
+  abstract get(): Promise<MemoryMessage<TAdditionalMessageOptions>[]>;
 
   /**
    * Store the messages in the memory block.

packages/core/src/memory/block/index.ts

@@ -1,4 +1,3 @@
 export { BaseMemoryBlock } from "./base";
 export { FactExtractionMemoryBlock } from "./fact";
 export { StaticMemoryBlock } from "./static";
-export { VectorMemoryBlock } from "./vector";

packages/core/src/memory/block/vector.ts

@@ -1,250 +0,0 @@
-import type { BaseEmbedding } from "../../embeddings";
-import type { BaseNodePostprocessor } from "../../postprocessor";
-import { BasePromptTemplate, defaultContextSystemPrompt } from "../../prompts";
-import type { NodeWithScore } from "../../schema";
-import { MetadataMode, TextNode } from "../../schema";
-import { extractText } from "../../utils/llms";
-import type {
-  BaseVectorStore,
-  MetadataFilter,
-  VectorStoreQuery,
-} from "../../vector-store";
-import { VectorStoreQueryMode } from "../../vector-store";
-import type { MemoryMessage } from "../types";
-import { BaseMemoryBlock, type MemoryBlockOptions } from "./base";
-
-/**
- * The options for the vector memory block.
- */
-export type VectorMemoryBlockOptions = {
-  /**
-   * The vector store to use for retrieval.
-   */
-  vectorStore: BaseVectorStore;
-
-  /**
-   * Maximum number of messages to include for context when retrieving.
-   * @default 5
-   */
-  retrievalContextWindow?: number;
-
-  /**
-   * Template for formatting the retrieved information.
-   * @default new PromptTemplate({ template: "{{ text }}" })
-   */
-  formatTemplate?: BasePromptTemplate;
-
-  /**
-   * List of node postprocessors to apply to the retrieved nodes containing messages.
-   *
-   * @default []
-   */
-  nodePostprocessors?: BaseNodePostprocessor[];
-
-  /**
-   * Configuration options for vector store queries when retrieving memory.
-   *
-   * @default
-   * ```typescript
-   * {
-   *   similarityTopK: 2,                    // Number of top similar results to return
-   *   mode: VectorStoreQueryMode.DEFAULT,   // Query mode for the vector store
-   *   sessionFilterKey: "session_id",       // Metadata key for session filtering
-   *   filters: {
-   *     filters: [
-   *       { key: "session_id", value: "<current block id>", operator: "==" }
-   *     ],
-   *     condition: "and"
-   *   }
-   * }
-   * ```
-   *
-   * Note: A session filter is automatically added to ensure memory isolation between blocks.
-   * If custom filters are provided, the session filter will be merged with them.
-   */
-  queryOptions?: Partial<VectorMemoryBlockQueryOptions>;
-} & MemoryBlockOptions;
-
-export type VectorMemoryBlockQueryOptions = Omit<
-  VectorStoreQuery,
-  "queryEmbedding" | "queryStr"
-> & {
-  sessionFilterKey: string;
-};
-
-/**
- * A memory block that retrieves relevant information from a vector store.
- *
- * This block stores conversation history in a vector store and retrieves
- * relevant information based on the most recent messages.
- */
-export class VectorMemoryBlock<
-  TAdditionalMessageOptions extends object = object,
-> extends BaseMemoryBlock<TAdditionalMessageOptions> {
-  private readonly vectorStore: BaseVectorStore;
-  private readonly retrievalContextWindow: number;
-  private readonly formatTemplate: BasePromptTemplate;
-  private readonly nodePostprocessors: BaseNodePostprocessor[];
-  private readonly queryOptions: VectorMemoryBlockQueryOptions;
-
-  constructor(options: VectorMemoryBlockOptions) {
-    super(options);
-
-    // Validate vector store
-    if (!options.vectorStore.storesText) {
-      throw new Error(
-        "vectorStore must store text to be used as a retrieval memory block",
-      );
-    }
-
-    this.vectorStore = options.vectorStore;
-    this.retrievalContextWindow = options.retrievalContextWindow ?? 5;
-    this.queryOptions = this.buildDefaultQueryOptions(options.queryOptions);
-    this.formatTemplate = options.formatTemplate ?? defaultContextSystemPrompt;
-    this.nodePostprocessors = options.nodePostprocessors ?? [];
-  }
-
-  get embedModel(): BaseEmbedding {
-    return this.vectorStore.embedModel;
-  }
-
-  async get(
-    messages: MemoryMessage<TAdditionalMessageOptions>[] = [],
-  ): Promise<MemoryMessage<TAdditionalMessageOptions>[]> {
-    if (messages?.length === 0) return [];
-
-    // Use the last message or a context window of messages for the query
-    let context: MemoryMessage<TAdditionalMessageOptions>[];
-    if (
-      this.retrievalContextWindow > 1 &&
-      messages.length >= this.retrievalContextWindow
-    ) {
-      context = messages.slice(-this.retrievalContextWindow);
-    } else {
-      context = messages;
-    }
-    const queryText = context
-      .map((message) => extractText(message.content))
-      .join("\n\n");
-    if (!queryText) return [];
-
-    // Create and execute the query
-    const queryEmbedding = await this.embedModel.getTextEmbedding(queryText);
-    const query: VectorStoreQuery = {
-      queryStr: queryText,
-      queryEmbedding,
-      ...this.queryOptions,
-    };
-    const results = await this.vectorStore.query(query);
-    if (!results.nodes?.length) return [];
-
-    // Create nodes with scores
-    const nodesWithScores: NodeWithScore[] = results.nodes.map(
-      (node, index) => ({
-        node,
-        score: results.similarities?.[index] ?? undefined,
-      }),
-    );
-
-    // Apply postprocessors
-    let processedNodes = nodesWithScores;
-    for (const postprocessor of this.nodePostprocessors) {
-      processedNodes = await postprocessor.postprocessNodes(
-        processedNodes,
-        queryText,
-      );
-    }
-
-    // Format the results
-    const retrievedText = processedNodes
-      .map(({ node }) => node.getContent(MetadataMode.NONE))
-      .join("\n\n");
-
-    const formattedText = this.formatTemplate.format({
-      context: retrievedText,
-    });
-
-    // Return as memory message
-    return [
-      {
-        id: this.id,
-        role: "memory",
-        content: formattedText,
-      } as MemoryMessage<TAdditionalMessageOptions>,
-    ];
-  }
-
-  async put(
-    messages: MemoryMessage<TAdditionalMessageOptions>[],
-  ): Promise<void> {
-    if (messages.length === 0) return;
-
-    // Format messages with role, text content, and additional info
-    const texts: string[] = [];
-
-    for (const message of messages) {
-      const text = extractText(message.content);
-      if (!text) continue;
-
-      let messageText = text;
-
-      // Add additional info if present
-      const additionalInfo = (message.options ?? {}) as Record<string, unknown>;
-      if (Object.keys(additionalInfo).length > 0) {
-        messageText += `\nAdditional Info: (${JSON.stringify(additionalInfo)})`;
-      }
-
-      texts.push(`<message role='${message.role}'>${messageText}</message>`);
-    }
-
-    if (texts.length === 0) return;
-
-    // Create text node with session metadata
-    const textNode = new TextNode({
-      text: texts.join("\n"),
-      metadata: { [this.queryOptions.sessionFilterKey]: this.id },
-    });
-
-    // Get embedding for the text
-    textNode.embedding = await this.embedModel.getTextEmbedding(textNode.text);
-
-    // Add to vector store
-    await this.vectorStore.add([textNode]);
-  }
-
-  private buildDefaultQueryOptions(
-    options: Partial<VectorMemoryBlockQueryOptions> | undefined,
-  ): VectorMemoryBlockQueryOptions {
-    const {
-      similarityTopK = 2,
-      mode = VectorStoreQueryMode.DEFAULT,
-      sessionFilterKey = "session_id",
-    } = options ?? {};
-
-    let filters = options?.filters;
-
-    const sessionFilter: MetadataFilter = {
-      key: sessionFilterKey,
-      value: this.id,
-      operator: "==",
-    };
-
-    if (filters) {
-      // Only add session_id filter if it doesn't exist in the filters list
-      const sessionIdFilterExists = filters.filters.some(
-        (filter) => filter.key === sessionFilterKey,
-      );
-      if (!sessionIdFilterExists) {
-        filters.filters.push(sessionFilter);
-      }
-    } else {
-      // If no filters are provided, add the session_id filter
-      filters = {
-        filters: [sessionFilter],
-        condition: "and",
-      };
-    }
-
-    return { ...options, similarityTopK, mode, sessionFilterKey, filters };
-  }
-}

packages/core/src/memory/factories.ts

@@ -8,10 +8,6 @@ import {
   StaticMemoryBlock,
   type StaticMemoryBlockOptions,
 } from "./block/static";
-import {
-  VectorMemoryBlock,
-  type VectorMemoryBlockOptions,
-} from "./block/vector";
 import { DEFAULT_TOKEN_LIMIT, Memory, type MemoryOptions } from "./memory";
 import type { MemoryMessage } from "./types";
 
@@ -119,17 +115,6 @@ export function factExtractionBlock<TMessageOptions extends object = object>(
   return new FactExtractionMemoryBlock<TMessageOptions>(options);
 }
 
-/**
- * create a VectorMemoryBlock
- * @param options - Configuration options for the vector memory block
- * @returns A new VectorMemoryBlock instance
- */
-export function vectorBlock<TMessageOptions extends object = object>(
-  options: VectorMemoryBlockOptions,
-): VectorMemoryBlock<TMessageOptions> {
-  return new VectorMemoryBlock<TMessageOptions>(options);
-}
-
 /**
  * Creates a new Memory instance from a snapshot
  * @param snapshot The snapshot to load from

packages/core/src/memory/memory.ts

@@ -31,13 +31,6 @@ export type MemoryOptions<TMessageOptions extends object = object> = {
    * Used internally for memory restoration from snapshots.
    */
   memoryCursor?: number;
-
-  /**
-   * The default LLM to use for memory retrieval.
-   * If not provided, the default `Settings.llm` will be used.
-   * This default LLM can be overridden by the LLM passed in the `getLLM` method.
-   */
-  llm?: LLM | undefined;
 };
 
 export class Memory<
@@ -72,10 +65,6 @@ export class Memory<
    * The cursor for the messages that have been processed into long-term memory.
    */
   private memoryCursor: number = 0;
-  /**
-   * The default LLM to use for memory retrieval.
-   */
-  private llm: LLM | undefined;
 
   constructor(
     messages: MemoryMessage<TMessageOptions>[] = [],
@@ -87,7 +76,6 @@ export class Memory<
       options.shortTermTokenLimitRatio ?? DEFAULT_SHORT_TERM_TOKEN_LIMIT_RATIO;
     this.memoryBlocks = options.memoryBlocks ?? [];
     this.memoryCursor = options.memoryCursor ?? 0;
-    this.initLLM(options.llm);
 
     this.adapters = {
       ...options.customAdapters,
@@ -96,15 +84,6 @@ export class Memory<
     } as TAdapters & BuiltinAdapters<TMessageOptions>;
   }
 
-  private initLLM(llm: LLM | undefined) {
-    // safe initialize LLM without throwing error if Settings.llm hasn't been set yet
-    try {
-      this.llm = llm ?? Settings.llm;
-    } catch (error) {
-      this.llm = undefined;
-    }
-  }
-
   /**
    * Add a message to the memory
    * @param message - The message to add to the memory
@@ -181,13 +160,12 @@ export class Memory<
   /**
    * Get the messages from the memory, optionally including transient messages.
    * only return messages that are within context window of the LLM
-   * @param llm - To fit the result messages to the context window of the LLM  (fallback to default llm if not provided).
-   * If llm is not specified in both the constructor and the method, the default token limit will be used.
+   * @param llm - To fit the result messages to the context window of the LLM. If not provided, the default token limit will be used.
    * @param transientMessages - Optional transient messages to include.
    * @returns The messages from the memory, optionally including transient messages.
    */
   async getLLM(
-    llm: LLM | undefined = this.llm,
+    llm?: LLM,
     transientMessages?: ChatMessage<TMessageOptions>[],
   ): Promise<ChatMessage[]> {
     // Priority of result messages:
@@ -198,20 +176,11 @@ export class Memory<
       ? Math.ceil(contextWindow * DEFAULT_TOKEN_LIMIT_RATIO)
       : this.tokenLimit;
 
-    let blockInputMessages = this.messages;
-    if (transientMessages && transientMessages.length > 0) {
-      blockInputMessages = [
-        ...this.messages,
-        ...transientMessages.map((m) => this.adapters.llamaindex.toMemory(m)),
-      ];
-    }
-
     // Start with fixed block messages (priority=0)
     // as it must always be included in the retrieval result
     const messages = await this.getMemoryBlockMessages(
       this.memoryBlocks.filter((block) => block.priority === 0),
       tokenLimit,
-      blockInputMessages,
     );
     // remaining token limit for short-term and memory blocks content
     const remainingTokenLimit =
@@ -238,7 +207,6 @@ export class Memory<
     const longTermBlockMessages = await this.getMemoryBlockMessages(
       longTermBlocks,
       memoryBlocksTokenLimit,
-      blockInputMessages,
     );
     messages.push(...longTermBlockMessages);
 
@@ -284,7 +252,6 @@ export class Memory<
   private async getMemoryBlockMessages(
     blocks: BaseMemoryBlock<TMessageOptions>[],
     tokenLimit?: number,
-    messages?: MemoryMessage<TMessageOptions>[],
   ): Promise<ChatMessage<TMessageOptions>[]> {
     if (blocks.length === 0) {
       return [];
@@ -298,7 +265,7 @@ export class Memory<
     let addedTokenCount = 0;
     for (const block of sortedBlocks) {
       try {
-        const content = await block.get(messages);
+        const content = await block.get();
         for (const message of content) {
           const chatMessage = this.adapters.llamaindex.fromMemory(message);
           const messageTokenCount = this.countMessagesToken([chatMessage]);

packages/core/src/vector-store/index.ts

@@ -101,9 +101,7 @@ export type VectorStoreByType = {
 };
 
 export type VectorStoreBaseParams = {
-  // @deprecated: use embedModel instead
   embeddingModel?: BaseEmbedding | undefined;
-  embedModel?: BaseEmbedding | undefined;
 };
 
 export abstract class BaseVectorStore<Client = unknown, T = unknown> {
@@ -119,8 +117,7 @@ export abstract class BaseVectorStore<Client = unknown, T = unknown> {
   ): Promise<VectorStoreQueryResult>;
 
   protected constructor(params?: VectorStoreBaseParams) {
-    this.embedModel =
-      params?.embedModel ?? params?.embeddingModel ?? Settings.embedModel;
+    this.embedModel = params?.embeddingModel ?? Settings.embedModel;
   }
 }
 

packages/experimental/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/experimental
 
-## 0.0.198
-
-### Patch Changes
-
-- llamaindex@0.11.21
-
 ## 0.0.197
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.198",
+  "version": "0.0.197",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,15 +1,5 @@
 # llamaindex
 
-## 0.11.21
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/cloud@4.0.26
-  - @llamaindex/node-parser@2.0.17
-  - @llamaindex/workflow@1.1.17
-
 ## 0.11.20
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.21",
+  "version": "0.11.20",
   "license": "MIT",
   "type": "module",
   "keywords": [

packages/llamaindex/src/vector-store/SimpleVectorStore.ts

@@ -272,7 +272,7 @@ export class SimpleVectorStore extends BaseVectorStore {
 
   static async fromPersistPath(
     persistPath: string,
-    embedModel?: BaseEmbedding,
+    embeddingModel?: BaseEmbedding,
   ): Promise<SimpleVectorStore> {
     const dirPath = path.dirname(persistPath);
     if (!(await exists(dirPath))) {
@@ -300,20 +300,20 @@ export class SimpleVectorStore extends BaseVectorStore {
     data.textIdToRefDocId = dataDict.textIdToRefDocId ?? {};
     // @ts-expect-error TS2322
     data.metadataDict = dataDict.metadataDict ?? {};
-    const store = new SimpleVectorStore({ data, embedModel });
+    const store = new SimpleVectorStore({ data, embeddingModel });
     store.persistPath = persistPath;
     return store;
   }
 
   static fromDict(
     saveDict: SimpleVectorStoreData,
-    embedModel?: BaseEmbedding,
+    embeddingModel?: BaseEmbedding,
   ): SimpleVectorStore {
     const data = new SimpleVectorStoreData();
     data.embeddingDict = saveDict.embeddingDict;
     data.textIdToRefDocId = saveDict.textIdToRefDocId;
     data.metadataDict = saveDict.metadataDict;
-    return new SimpleVectorStore({ data, embedModel });
+    return new SimpleVectorStore({ data, embeddingModel });
   }
 
   toDict(): SimpleVectorStoreData {

packages/llamaindex/tests/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/core-test
 
-## 0.1.13
-
-### Patch Changes
-
-- @llamaindex/openai@0.4.12
-
 ## 0.1.12
 
 ### Patch Changes

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.13",
+  "version": "0.1.12",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/llamaindex/tests/vector-stores/SimpleVectorStore.test.ts

@@ -59,7 +59,7 @@ describe("SimpleVectorStore", () => {
       }),
     ];
     store = new SimpleVectorStore({
-      embedModel: {} as BaseEmbedding, // Mocking the embedModel
+      embeddingModel: {} as BaseEmbedding, // Mocking the embedModel
       data: {
         embeddingDict: {},
         textIdToRefDocId: {},

packages/node-parser/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/node-parser
 
-## 2.0.17
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 2.0.16
 
 ### Patch Changes

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "2.0.17",
+  "version": "2.0.16",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {

packages/providers/anthropic/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/anthropic
 
-## 0.3.19
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.3.18
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.3.19",
+  "version": "0.3.18",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/assemblyai/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/assemblyai
 
-## 0.1.16
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.15
 
 ### Patch Changes

packages/providers/assemblyai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/assemblyai",
   "description": "AssemblyAI Reader for LlamaIndex",
-  "version": "0.1.16",
+  "version": "0.1.15",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/aws/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/community
 
-## 0.0.112
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.111
 
 ### Patch Changes

packages/providers/aws/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/aws",
   "description": "AWS package for LlamaIndexTS",
-  "version": "0.0.112",
+  "version": "0.0.111",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/providers/clip/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/clip
 
-## 0.0.68
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.0.67
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.68",
+  "version": "0.0.67",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/cohere/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/cohere
 
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.30
 
 ### Patch Changes

packages/providers/cohere/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/cohere",
   "description": "Cohere Adapter for LlamaIndex",
-  "version": "0.0.31",
+  "version": "0.0.30",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/deepinfra
 
-## 0.0.68
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.0.67
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.68",
+  "version": "0.0.67",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/deepseek
 
-## 0.0.29
-
-### Patch Changes
-
-- @llamaindex/openai@0.4.12
-
 ## 0.0.28
 
 ### Patch Changes

packages/providers/deepseek/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepseek",
   "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.29",
+  "version": "0.0.28",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/discord/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/discord
 
-## 0.1.16
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.15
 
 ### Patch Changes

packages/providers/discord/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/discord",
   "description": "Discord Reader for LlamaIndex",
-  "version": "0.1.16",
+  "version": "0.1.15",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/excel/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/excel
 
-## 0.1.17
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.16
 
 ### Patch Changes

packages/providers/excel/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/excel",
   "description": "Excel Reader for LlamaIndex",
-  "version": "0.1.17",
+  "version": "0.1.16",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/fireworks/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/fireworks
 
-## 0.0.28
-
-### Patch Changes
-
-- @llamaindex/openai@0.4.12
-
 ## 0.0.27
 
 ### Patch Changes

packages/providers/fireworks/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/fireworks",
   "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.28",
+  "version": "0.0.27",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/google
 
-## 0.3.16
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.3.15
 
 ### Patch Changes

packages/providers/google/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/google",
   "description": "Google Adapter for LlamaIndex",
-  "version": "0.3.16",
+  "version": "0.3.15",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/groq/CHANGELOG.md

@@ -1,11 +1,5 @@
 # @llamaindex/groq
 
-## 0.0.84
-
-### Patch Changes
-
-- @llamaindex/openai@0.4.12
-
 ## 0.0.83
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.84",
+  "version": "0.0.83",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/huggingface
 
-## 0.1.22
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.1.21
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.1.22",
+  "version": "0.1.21",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/jinaai/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/jinaai
 
-## 0.0.28
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.0.27
 
 ### Patch Changes

packages/providers/jinaai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/jinaai",
   "description": "JinaAI Adapter for LlamaIndex",
-  "version": "0.0.28",
+  "version": "0.0.27",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/mistral/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/mistral
 
-## 0.1.17
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.16
 
 ### Patch Changes

packages/providers/mistral/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mistral",
   "description": "Mistral Adapter for LlamaIndex",
-  "version": "0.1.17",
+  "version": "0.1.16",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/mixedbread/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/mixedbread
 
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.30
 
 ### Patch Changes

packages/providers/mixedbread/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mixedbread",
   "description": "Mixedbread Adapter for LlamaIndex",
-  "version": "0.0.31",
+  "version": "0.0.30",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/notion/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/notion
 
-## 0.1.16
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.15
 
 ### Patch Changes

packages/providers/notion/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/notion",
   "description": "Notion Reader for LlamaIndex",
-  "version": "0.1.16",
+  "version": "0.1.15",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/ollama/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/ollama
 
-## 0.1.17
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.1.16
 
 ### Patch Changes

packages/providers/ollama/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/ollama",
   "description": "Ollama Adapter for LlamaIndex",
-  "version": "0.1.17",
+  "version": "0.1.16",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/openai
 
-## 0.4.12
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.4.11
 
 ### Patch Changes

packages/providers/openai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/openai",
   "description": "OpenAI Adapter for LlamaIndex",
-  "version": "0.4.12",
+  "version": "0.4.11",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/tests/chat.test.ts

@@ -1,9 +1,5 @@
-import {
-  ChatMessage,
-  ChatResponseChunk,
-  ToolCallLLMMessageOptions,
-} from "@llamaindex/core/llms";
-import { describe, expect, it, vi } from "vitest";
+import { ChatMessage, ToolCallLLMMessageOptions } from "@llamaindex/core/llms";
+import { describe, expect, it } from "vitest";
 import { z } from "zod";
 import { OpenAI } from "../src/llm";
 
@@ -235,52 +231,3 @@ describe("OpenAI Static Methods", () => {
     });
   });
 });
-
-describe("OpenAI streamChat", () => {
-  it("should handle choice with empty delta and finish_reason stop", async () => {
-    // Create a mock OpenAI instance
-    const mockStream = async function* () {
-      yield {
-        choices: [
-          {
-            delta: {},
-            finish_reason: "stop",
-            index: 0,
-            logprobs: null,
-          },
-        ],
-      };
-    };
-
-    // Mock the OpenAI session and chat completions
-    const mockSession = {
-      chat: {
-        completions: {
-          create: vi.fn().mockResolvedValue(mockStream()),
-        },
-      },
-    };
-
-    const openai = new OpenAI({
-      model: "gpt-4o-mini",
-      apiKey: "test-key",
-      // @ts-expect-error: mockSession is a mock object for testing purposes
-      session: mockSession,
-    });
-
-    // @ts-expect-error accessing protected method
-    const stream = openai.streamChat({
-      messages: [{ role: "user" as const, content: "Hello" }],
-      stream: true,
-    });
-
-    const chunks: ChatResponseChunk[] = [];
-    for await (const chunk of stream) {
-      chunks.push(chunk);
-    }
-
-    expect(chunks).toHaveLength(1);
-    expect(chunks[0].options).toEqual({});
-    expect(chunks[0].delta).toBe("");
-  });
-});

packages/providers/perplexity/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/perplexity
 
-## 0.0.25
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.0.24
 
 ### Patch Changes

packages/providers/perplexity/package.json

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

packages/providers/portkey-ai/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/portkey-ai
 
-## 0.0.59
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.58
 
 ### Patch Changes

packages/providers/portkey-ai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/portkey-ai",
   "description": "Portkey Adapter for LlamaIndex",
-  "version": "0.0.59",
+  "version": "0.0.58",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/replicate/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/replicate
 
-## 0.0.59
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.58
 
 ### Patch Changes

packages/providers/replicate/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/replicate",
   "description": "Replicate Adapter for LlamaIndex",
-  "version": "0.0.59",
+  "version": "0.0.58",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/retriever/bm25/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/bm25-retriever
 
-## 0.0.6
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.5
 
 ### Patch Changes

packages/providers/retriever/bm25/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/bm25-retriever",
   "description": "BM25 Retriever for LlamaIndex",
-  "version": "0.0.6",
+  "version": "0.0.5",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/storage/astra/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/astra
 
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.30
 
 ### Patch Changes

packages/providers/storage/astra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/astra",
   "description": "Astra Storage for LlamaIndex",
-  "version": "0.0.31",
+  "version": "0.0.30",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/storage/azure/CHANGELOG.md

@@ -1,13 +1,5 @@
 # @llamaindex/azure
 
-## 0.1.29
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-  - @llamaindex/openai@0.4.12
-
 ## 0.1.28
 
 ### Patch Changes

packages/providers/storage/azure/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/azure",
   "description": "Azure Storage for LlamaIndex",
-  "version": "0.1.29",
+  "version": "0.1.28",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/storage/chroma/CHANGELOG.md

@@ -1,12 +1,5 @@
 # @llamaindex/chroma
 
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
-
 ## 0.0.30
 
 ### Patch Changes