The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Fix typescript docs (#3357)
Parshva Daftariee00bd5731da
diff --git a/docs/changelog.mdx b/docs/changelog.mdxindex 81b0cf300..947d4416b 100644--- a/docs/changelog.mdx+++ b/docs/changelog.mdx@@ -7,9 +7,9 @@ mode: "wide"<Tabs><Tab title="Python">-<Update label="2025-07-24" description="v0.1.116">+<Update label="2025-08-14" description="v0.1.116">-**New Features:**+**New Features & Updates:**- **Pinecone:** Added namespace support and improved type safety- **Milvus:** Added db_name field to MilvusDBConfig- **Vector Stores:** Added multi-id filters support@@ -19,17 +19,36 @@ mode: "wide"- **LLM Monitoring:** Added monitoring callback support**Improvements:**-- **Performance:** Improved async handling in AsyncMemory class-- **Documentation:** Added async add announcement, personalized search docs, Neptune examples, V5 migration docs-- **Configuration:** Refactored base class config for LLMs, added sslmode for pgvector-- **Dependencies:** Updated psycopg to version 3, updated Docker compose+- **Performance:**+ - Improved async handling in AsyncMemory class+- **Documentation:**+ - Added async add announcement+ - Added personalized search docs+ - Added Neptune examples+ - Added V5 migration docs+- **Configuration:**+ - Refactored base class config for LLMs+ - Added sslmode for pgvector+- **Dependencies:**+ - Updated psycopg to version 3+ - Updated Docker compose**Bug Fixes:**-- **Tests:** Fixed failing tests and restricted package versions-- **Memgraph:** Fixed async attribute errors, n_embeddings usage, and indexing issues-- **Vector Stores:** Fixed Qdrant cloud indexing, Neo4j Cypher syntax, and LLM parameters-- **Graph Store:** Fixed LM config prioritization-- **Dependencies:** Fixed JSON import for psycopg+- **Tests:**+ - Fixed failing tests+ - Restricted package versions+- **Memgraph:**+ - Fixed async attribute errors+ - Fixed n_embeddings usage+ - Fixed indexing issues+- **Vector Stores:**+ - Fixed Qdrant cloud indexing+ - Fixed Neo4j Cypher syntax+ - Fixed LLM parameters+- **Graph Store:**+ - Fixed LM config prioritization+- **Dependencies:**+ - Fixed JSON import for psycopg**Refactoring:**- **Google AI:** Refactored from Gemini to Google AIdiff --git a/docs/components/embedders/models/google_AI.mdx b/docs/components/embedders/models/google_AI.mdxindex 7ce9024d3..9efd41b2e 100644--- a/docs/components/embedders/models/google_AI.mdx+++ b/docs/components/embedders/models/google_AI.mdx@@ -6,7 +6,8 @@ To use Google AI embedding models, set the `GOOGLE_API_KEY` environment variable### Usage-```python+<CodeGroup>+```python Pythonimport osfrom mem0 import Memory@@ -26,12 +27,37 @@ m = Memory.from_config(config)messages = [{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},- {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]m.add(messages, user_id="john")```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';++const config = {+ embedder: {+ provider: 'google',+ config: {+ apiKey: process.env.GOOGLE_API_KEY || '',+ model: 'text-embedding-004',+ // The output dimensionality is fixed at 768 for Google AI embeddings+ },+ },+};++const memory = new Memory(config);+const messages = [+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}+]+await memory.add(messages, { userId: "john" });+```+</CodeGroup>+### ConfigHere are the parameters available for configuring Gemini embedder:diff --git a/docs/components/embedders/models/langchain.mdx b/docs/components/embedders/models/langchain.mdxindex aa48ae265..74ad18573 100644--- a/docs/components/embedders/models/langchain.mdx+++ b/docs/components/embedders/models/langchain.mdx@@ -44,29 +44,33 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})``````typescript TypeScript-import { Memory } from "mem0ai";+import { Memory } from 'mem0ai/oss';import { OpenAIEmbeddings } from "@langchain/openai";-const embeddings = new OpenAIEmbeddings();+// Initialize a LangChain embeddings model directly+const openaiEmbeddings = new OpenAIEmbeddings({+ modelName: "text-embedding-3-small",+ dimensions: 1536,+ apiKey: process.env.OPENAI_API_KEY,+});+const config = {- "embedder": {- "provider": "langchain",- "config": {- "model": embeddings- }- }-}+ embedder: {+ provider: 'langchain',+ config: {+ model: openaiEmbeddings,+ },+ },+};const memory = new Memory(config);-const messages = [- { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },- { role: "assistant", content: "How about a thriller movies? They can be quite engaging." },- { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },- { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]--memory.add(messages, user_id="alice", metadata={"category": "movies"})+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });```</CodeGroup>@@ -96,9 +100,10 @@ When using LangChain as an embedder provider, you'll need to:### Examples with Different Providers+<CodeGroup>#### HuggingFace Embeddings-```python+```python Pythonfrom langchain_huggingface import HuggingFaceEmbeddings# Initialize a HuggingFace embeddings model@@ -117,9 +122,33 @@ config = {}```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';+import { HuggingFaceEmbeddings } from "@langchain/community/embeddings/hf";++// Initialize a HuggingFace embeddings model+const hfEmbeddings = new HuggingFaceEmbeddings({+ modelName: "BAAI/bge-small-en-v1.5",+ encode: {+ normalize_embeddings: true,+ },+});++const config = {+ embedder: {+ provider: 'langchain',+ config: {+ model: hfEmbeddings,+ },+ },+};+```+</CodeGroup>++<CodeGroup>#### Ollama Embeddings-```python+```python Pythonfrom langchain_ollama import OllamaEmbeddings# Initialize an Ollama embeddings model@@ -137,6 +166,27 @@ config = {}```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';+import { OllamaEmbeddings } from "@langchain/community/embeddings/ollama";++// Initialize an Ollama embeddings model+const ollamaEmbeddings = new OllamaEmbeddings({+ model: "nomic-embed-text",+ baseUrl: "http://localhost:11434", // Ollama server URL+});++const config = {+ embedder: {+ provider: 'langchain',+ config: {+ model: ollamaEmbeddings,+ },+ },+};+```+</CodeGroup>+<Note>Make sure to install the necessary LangChain packages and any provider-specific dependencies.</Note>diff --git a/docs/components/embedders/models/ollama.mdx b/docs/components/embedders/models/ollama.mdxindex d2829a8ee..4e1a4d331 100644--- a/docs/components/embedders/models/ollama.mdx+++ b/docs/components/embedders/models/ollama.mdx@@ -2,7 +2,8 @@ You can use embedding models from Ollama to run Mem0 locally.### Usage-```python+<CodeGroup>+```python Pythonimport osfrom mem0 import Memory@@ -21,18 +22,52 @@ m = Memory.from_config(config)messages = [{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},- {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]m.add(messages, user_id="john")```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';++const config = {+ embedder: {+ provider: 'ollama',+ config: {+ model: 'nomic-embed-text:latest', // or any other Ollama embedding model+ url: 'http://localhost:11434', // Ollama server URL+ },+ },+};++const memory = new Memory(config);+const messages = [+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}+]+await memory.add(messages, { userId: "john" });+```+</CodeGroup>+### ConfigHere are the parameters available for configuring Ollama embedder:+<Tabs>+<Tab title="Python">| Parameter | Description | Default Value || --- | --- | --- |-| `model` | The name of the OpenAI model to use | `nomic-embed-text` |+| `model` | The name of the Ollama model to use | `nomic-embed-text` || `embedding_dims` | Dimensions of the embedding model | `512` |-| `ollama_base_url` | Base URL for ollama connection | `None` |\ No newline at end of file+| `ollama_base_url` | Base URL for ollama connection | `None` |+</Tab>+<Tab title="TypeScript">+| Parameter | Description | Default Value |+| --- | --- | --- |+| `model` | The name of the Ollama model to use | `nomic-embed-text:latest` |+| `url` | Base URL for Ollama server | `http://localhost:11434` |+</Tab>+</Tabs>\ No newline at end of filediff --git a/docs/components/llms/models/langchain.mdx b/docs/components/llms/models/langchain.mdxindex c8f4eaa1f..624d86425 100644--- a/docs/components/llms/models/langchain.mdx+++ b/docs/components/llms/models/langchain.mdx@@ -46,34 +46,34 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})``````typescript TypeScript-import { Memory } from "mem0ai";+import { Memory } from 'mem0ai/oss';import { ChatOpenAI } from "@langchain/openai";-const openai_model = new ChatOpenAI({- model: "gpt-4o",+// Initialize a LangChain model directly+const openaiModel = new ChatOpenAI({+ modelName: "gpt-4",temperature: 0.2,- max_tokens: 2000-})+ maxTokens: 2000,+ apiKey: process.env.OPENAI_API_KEY,+});const config = {- "llm": {- "provider": "langchain",- "config": {- "model": openai_model- }- }-}+ llm: {+ provider: 'langchain',+ config: {+ model: openaiModel,+ },+ },+};const memory = new Memory(config);-const messages = [- { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },- { role: "assistant", content: "How about a thriller movies? They can be quite engaging." },- { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },- { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]--memory.add(messages, user_id="alice", metadata={"category": "movies"})+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });```</CodeGroup>diff --git a/docs/components/llms/models/ollama.mdx b/docs/components/llms/models/ollama.mdxindex 757fd2cc0..9c0cd73cf 100644--- a/docs/components/llms/models/ollama.mdx+++ b/docs/components/llms/models/ollama.mdx@@ -2,7 +2,8 @@ You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.## Usage-```python+<CodeGroup>+```python Pythonimport osfrom mem0 import Memory@@ -23,12 +24,37 @@ m = Memory.from_config(config)messages = [{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},- {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]m.add(messages, user_id="alice", metadata={"category": "movies"})```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';++const config = {+ llm: {+ provider: 'ollama',+ config: {+ model: 'llama3.1:8b', // or any other Ollama model+ url: 'http://localhost:11434', // Ollama server URL+ temperature: 0.1,+ },+ },+};++const memory = new Memory(config);+const messages = [+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}+]+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });+```+</CodeGroup>+## ConfigAll available parameters for the `ollama` config are present in [Master List of All Params in Config](../config).\ No newline at end of filediff --git a/docs/components/vectordbs/dbs/pgvector.mdx b/docs/components/vectordbs/dbs/pgvector.mdxindex 6a083af5c..03836c2db 100644--- a/docs/components/vectordbs/dbs/pgvector.mdx+++ b/docs/components/vectordbs/dbs/pgvector.mdx@@ -2,7 +2,8 @@### Usage-```python+<CodeGroup>+```python Pythonimport osfrom mem0 import Memory@@ -24,12 +25,43 @@ m = Memory.from_config(config)messages = [{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},- {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}]m.add(messages, user_id="alice", metadata={"category": "movies"})```+```typescript TypeScript+import { Memory } from 'mem0ai/oss';++const config = {+ vectorStore: {+ provider: 'pgvector',+ config: {+ collectionName: 'memories',+ embeddingModelDims: 1536,+ user: 'test',+ password: '123',+ host: '127.0.0.1',+ port: 5432,+ dbname: 'vector_store', // Optional, defaults to 'postgres'+ diskann: false, // Optional, requires pgvectorscale extension+ hnsw: false, // Optional, for HNSW indexing+ },+ },+};++const memory = new Memory(config);+const messages = [+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},+ {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},+ {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}+]+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });+```+</CodeGroup>+### ConfigHere's the parameters available for configuring pgvector: