Merge remote-tracking branch 'origin/main' into docs/stale-rerankers
# Conflicts: # docs/components/rerankers/models/llm.mdx
This commit is contained in:
kartik-mem0
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: "FastEmbed"
|
||||
description: "Configure FastEmbed as an embedding provider in Mem0 to generate embeddings locally using ONNX-based models without a GPU."
|
||||
---
|
||||
|
||||
You can use FastEmbed to run embedding models locally in Mem0. FastEmbed is an ONNX-based embedding library that runs efficiently on CPU without requiring a GPU or an external API key.
|
||||
|
||||
### Installation
|
||||
|
||||
```bash
|
||||
pip install fastembed
|
||||
```
|
||||
|
||||
### Usage
|
||||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
import os
|
||||
from mem0 import Memory
|
||||
|
||||
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
|
||||
|
||||
config = {
|
||||
"embedder": {
|
||||
"provider": "fastembed",
|
||||
"config": {
|
||||
"model": "thenlper/gte-large"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about 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."}
|
||||
]
|
||||
m.add(messages, user_id="john")
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Config
|
||||
|
||||
Here are the parameters available for configuring FastEmbed embedder:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
| `model` | The name of the FastEmbed model to use | `thenlper/gte-large` |
|
||||
| `embedding_dims` | Dimensions of the embedding model (auto-derived from the model if not set) | `None` |
|
||||
@@ -4,9 +4,12 @@ description: "Use LiteLLM as an LLM provider in Mem0 to access over 100 language
|
||||
---
|
||||
[Litellm](https://litellm.vercel.app/docs/) is compatible with over 100 large language models (LLMs), all using a standardized input/output format. You can explore the [available models](https://litellm.vercel.app/docs/providers) to use with Litellm. Ensure you set the `API_KEY` for the model you choose to use.
|
||||
|
||||
In the TypeScript SDK, run LiteLLM as a [proxy server](https://docs.litellm.ai/docs/simple_proxy) (an OpenAI-compatible endpoint) and point Mem0 at it via `LITELLM_API_BASE` (defaults to `http://localhost:4000`).
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
import os
|
||||
from mem0 import Memory
|
||||
|
||||
@@ -33,6 +36,33 @@ messages = [
|
||||
m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
import { Memory } from 'mem0ai/oss';
|
||||
|
||||
// Point Mem0 at your LiteLLM proxy. apiKey defaults to "sk-anything"
|
||||
// (the proxy handles real auth); baseURL defaults to http://localhost:4000.
|
||||
const config = {
|
||||
llm: {
|
||||
provider: 'litellm',
|
||||
config: {
|
||||
apiKey: process.env.LITELLM_API_KEY || 'sk-anything',
|
||||
baseURL: process.env.LITELLM_API_BASE || 'http://localhost:4000',
|
||||
model: 'gpt-5-mini',
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
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 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>
|
||||
|
||||
## Config
|
||||
|
||||
All available parameters for the `litellm` config are present in [Master List of All Params in Config](../config).
|
||||
@@ -7,7 +7,8 @@ To use MiniMax LLM models, you have to set the `MINIMAX_API_KEY` environment var
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
import os
|
||||
from mem0 import Memory
|
||||
|
||||
@@ -36,9 +37,37 @@ messages = [
|
||||
m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
import { Memory } from 'mem0ai/oss';
|
||||
|
||||
const config = {
|
||||
llm: {
|
||||
provider: 'minimax',
|
||||
config: {
|
||||
apiKey: process.env.MINIMAX_API_KEY || '',
|
||||
model: 'MiniMax-M2.7',
|
||||
temperature: 0.2,
|
||||
maxTokens: 2000,
|
||||
topP: 1.0,
|
||||
},
|
||||
},
|
||||
};
|
||||
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 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>
|
||||
|
||||
You can also configure the API base URL in the config:
|
||||
|
||||
```python
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
config = {
|
||||
"llm": {
|
||||
"provider": "minimax",
|
||||
@@ -51,6 +80,20 @@ config = {
|
||||
}
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
const config = {
|
||||
llm: {
|
||||
provider: 'minimax',
|
||||
config: {
|
||||
model: 'MiniMax-M2.7',
|
||||
baseURL: 'https://your-custom-endpoint.com',
|
||||
apiKey: 'your-api-key', // alternatively to using the environment variable
|
||||
},
|
||||
},
|
||||
};
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Config
|
||||
|
||||
All available parameters for the `minimax` config are present in [Master List of All Params in Config](../config).
|
||||
|
||||
@@ -1,226 +0,0 @@
|
||||
---
|
||||
title: LLM as Reranker
|
||||
description: "Use any LLM as a flexible reranker in Mem0 with custom prompts and domain-specific scoring logic."
|
||||
---
|
||||
|
||||
<Warning>
|
||||
**This page has been superseded.** Please see [LLM Reranker](/components/rerankers/models/llm_reranker) for the complete and up-to-date documentation on using LLMs for reranking.
|
||||
</Warning>
|
||||
|
||||
LLM-based reranker provides maximum flexibility by using any Large Language Model to score document relevance. This approach allows for custom prompts and domain-specific scoring logic.
|
||||
|
||||
## Supported LLM Providers
|
||||
|
||||
Any LLM provider supported by Mem0 can be used for reranking:
|
||||
|
||||
- **OpenAI**: GPT-4, GPT-3.5-turbo, etc.
|
||||
- **Anthropic**: Claude models
|
||||
- **Together**: Open-source models
|
||||
- **Groq**: Fast inference
|
||||
- **Ollama**: Local models
|
||||
- And more...
|
||||
|
||||
## Configuration
|
||||
|
||||
```python Python
|
||||
from mem0 import Memory
|
||||
|
||||
config = {
|
||||
"vector_store": {
|
||||
"provider": "chroma",
|
||||
"config": {
|
||||
"collection_name": "my_memories",
|
||||
"path": "./chroma_db"
|
||||
}
|
||||
},
|
||||
"llm": {
|
||||
"provider": "openai",
|
||||
"config": {
|
||||
"model": "gpt-4o-mini"
|
||||
}
|
||||
},
|
||||
"reranker": {
|
||||
"provider": "llm",
|
||||
"config": {
|
||||
"model": "gpt-4o-mini",
|
||||
"provider": "openai",
|
||||
"api_key": "your-openai-api-key", # or set OPENAI_API_KEY
|
||||
"top_k": 5,
|
||||
"temperature": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
memory = Memory.from_config(config)
|
||||
```
|
||||
|
||||
## Custom Scoring Prompt
|
||||
|
||||
You can provide a custom prompt for relevance scoring:
|
||||
|
||||
```python Python
|
||||
custom_prompt = """You are a relevance scoring assistant. Rate how well this document answers the query.
|
||||
|
||||
Query: "{query}"
|
||||
Document: "{document}"
|
||||
|
||||
Score from 0.0 to 1.0 where:
|
||||
- 1.0: Perfect match, directly answers the query
|
||||
- 0.8-0.9: Highly relevant, good match
|
||||
- 0.6-0.7: Moderately relevant, partial match
|
||||
- 0.4-0.5: Slightly relevant, limited useful information
|
||||
- 0.0-0.3: Not relevant or no useful information
|
||||
|
||||
Provide only a single numerical score between 0.0 and 1.0."""
|
||||
|
||||
config["reranker"]["config"]["scoring_prompt"] = custom_prompt
|
||||
```
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python Python
|
||||
import os
|
||||
from mem0 import Memory
|
||||
|
||||
# Set API key
|
||||
os.environ["OPENAI_API_KEY"] = "your-api-key"
|
||||
|
||||
# Initialize memory with LLM reranker
|
||||
config = {
|
||||
"vector_store": {"provider": "chroma"},
|
||||
"llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
|
||||
"reranker": {
|
||||
"provider": "llm",
|
||||
"config": {
|
||||
"model": "gpt-4o-mini",
|
||||
"provider": "openai",
|
||||
"temperature": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
memory = Memory.from_config(config)
|
||||
|
||||
# Add memories
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm learning Python programming"},
|
||||
{"role": "user", "content": "I find object-oriented programming challenging"},
|
||||
{"role": "user", "content": "I love hiking in national parks"}
|
||||
]
|
||||
|
||||
memory.add(messages, user_id="david")
|
||||
|
||||
# Search with LLM reranking
|
||||
results = memory.search("What programming topics is the user studying?", filters={"user_id": "david"}, rerank=True)
|
||||
|
||||
for result in results['results']:
|
||||
print(f"Memory: {result['memory']}")
|
||||
print(f"Vector Score: {result['score']:.3f}")
|
||||
print(f"Rerank Score: {result['rerank_score']:.3f}")
|
||||
print()
|
||||
```
|
||||
|
||||
```text Output
|
||||
Memory: I'm learning Python programming
|
||||
Vector Score: 0.856
|
||||
Rerank Score: 0.920
|
||||
|
||||
Memory: I find object-oriented programming challenging
|
||||
Vector Score: 0.782
|
||||
Rerank Score: 0.850
|
||||
```
|
||||
|
||||
## Domain-Specific Scoring
|
||||
|
||||
Create specialized scoring for your domain:
|
||||
|
||||
```python Python
|
||||
medical_prompt = """You are a medical relevance expert. Score how relevant this medical record is to the clinical query.
|
||||
|
||||
Clinical Query: "{query}"
|
||||
Medical Record: "{document}"
|
||||
|
||||
Consider:
|
||||
- Clinical relevance and accuracy
|
||||
- Patient safety implications
|
||||
- Diagnostic value
|
||||
- Treatment relevance
|
||||
|
||||
Score from 0.0 to 1.0. Provide only the numerical score."""
|
||||
|
||||
config = {
|
||||
"reranker": {
|
||||
"provider": "llm",
|
||||
"config": {
|
||||
"model": "gpt-4o-mini",
|
||||
"provider": "openai",
|
||||
"scoring_prompt": medical_prompt,
|
||||
"temperature": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Multiple LLM Providers
|
||||
|
||||
Use different LLM providers for reranking:
|
||||
|
||||
```python Python
|
||||
# Using Anthropic Claude
|
||||
anthropic_config = {
|
||||
"reranker": {
|
||||
"provider": "llm",
|
||||
"config": {
|
||||
"model": "claude-3-haiku-20240307",
|
||||
"provider": "anthropic",
|
||||
"temperature": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Using local Ollama model
|
||||
ollama_config = {
|
||||
"reranker": {
|
||||
"provider": "llm",
|
||||
"config": {
|
||||
"model": "llama2:7b",
|
||||
"provider": "ollama",
|
||||
"temperature": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Configuration Parameters
|
||||
|
||||
| Parameter | Description | Type | Default |
|
||||
|-----------|-------------|------|---------|
|
||||
| `model` | LLM model to use for scoring | `str` | `"gpt-4o-mini"` |
|
||||
| `provider` | LLM provider name | `str` | `"openai"` |
|
||||
| `api_key` | API key for the LLM provider | `str` | `None` |
|
||||
| `top_k` | Maximum documents to return | `int` | `None` |
|
||||
| `temperature` | Temperature for LLM generation | `float` | `0.0` |
|
||||
| `max_tokens` | Maximum tokens for LLM response | `int` | `100` |
|
||||
| `scoring_prompt` | Custom prompt template | `str` | Default prompt |
|
||||
|
||||
## Advantages
|
||||
|
||||
- **Maximum Flexibility**: Custom prompts for any use case
|
||||
- **Domain Expertise**: Leverage LLM knowledge for specialized domains
|
||||
- **Interpretability**: Understand scoring through prompt engineering
|
||||
- **Multi-criteria**: Score based on multiple relevance factors
|
||||
|
||||
## Considerations
|
||||
|
||||
- **Latency**: Higher latency than specialized rerankers
|
||||
- **Cost**: LLM API costs per reranking operation
|
||||
- **Consistency**: May have slight variations in scoring
|
||||
- **Prompt Engineering**: Requires careful prompt design
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Temperature**: Use 0.0 for consistent scoring
|
||||
2. **Prompt Design**: Be specific about scoring criteria
|
||||
3. **Token Efficiency**: Keep prompts concise to reduce costs
|
||||
4. **Caching**: Cache results for repeated queries when possible
|
||||
5. **Fallback**: Handle API errors gracefully
|
||||
@@ -46,7 +46,7 @@ Here are the parameters available for configuring Baidu VectorDB:
|
||||
| `account` | Baidu VectorDB account name | `root` |
|
||||
| `api_key` | API key for accessing Baidu VectorDB | Required |
|
||||
| `database_name` | Name of the database | `mem0` |
|
||||
| `table_name` | Name of the table | `mem0_table` |
|
||||
| `table_name` | Name of the table | `mem0` |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||||
| `metric_type` | Distance metric for similarity search | `L2` |
|
||||
|
||||
|
||||
@@ -56,6 +56,8 @@ Here are the parameters available for configuring Elasticsearch:
|
||||
| `api_key` | API key for authentication | `None` |
|
||||
| `user` | Username for basic authentication | `None` |
|
||||
| `password` | Password for basic authentication | `None` |
|
||||
| `use_ssl` | Whether to use SSL for the connection | `True` |
|
||||
| `ca_certs` | Path to CA bundle for SSL certificate verification | `None` |
|
||||
| `verify_certs` | Whether to verify SSL certificates | `True` |
|
||||
| `auto_create_index` | Whether to automatically create the index | `True` |
|
||||
| `custom_search_query` | Function returning a custom search query | `None` |
|
||||
|
||||
@@ -55,6 +55,7 @@ Here are the parameters available for configuring FAISS:
|
||||
| `path` | Path to store FAISS index and metadata | `/tmp/faiss/<collection_name>` |
|
||||
| `distance_strategy` | Distance metric strategy to use (options: 'euclidean', 'inner_product', 'cosine') | `euclidean` |
|
||||
| `normalize_L2` | Whether to normalize L2 vectors (only applicable for euclidean distance) | `False` |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||||
|
||||
### Performance Considerations
|
||||
|
||||
|
||||
@@ -47,12 +47,12 @@ 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";
|
||||
import { MemoryVectorStore as LangchainMemoryStore } from "langchain/vectorstores/memory";
|
||||
import { MemoryVectorStore } from "langchain/vectorstores/memory";
|
||||
|
||||
const embeddings = new OpenAIEmbeddings();
|
||||
const vectorStore = new LangchainVectorStore(embeddings);
|
||||
const vectorStore = new MemoryVectorStore(embeddings);
|
||||
|
||||
const config = {
|
||||
"vector_store": {
|
||||
|
||||
@@ -42,8 +42,8 @@ Here are the parameters available for configuring MongoDB:
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
| db_name | Name of the MongoDB database | `"mem0_db"` |
|
||||
| collection_name | Name of the MongoDB collection | `"mem0_collection"` |
|
||||
| collection_name | Name of the MongoDB collection | `"mem0"` |
|
||||
| embedding_model_dims | Dimensions of the embedding vectors | `1536` |
|
||||
| mongo_uri | The MongoDB URI connection string | `mongodb://username:password@localhost:27017` |
|
||||
| mongo_uri | The MongoDB URI connection string | `mongodb://localhost:27017` |
|
||||
|
||||
> **Note**: If `mongo_uri` is not provided, it will default to `mongodb://username:password@localhost:27017`.
|
||||
> **Note**: If `mongo_uri` is not provided, it will default to `mongodb://localhost:27017`.
|
||||
|
||||
@@ -53,17 +53,14 @@ print(results)
|
||||
import "dotenv/config";
|
||||
import { Memory } from "mem0ai/oss";
|
||||
|
||||
const databaseUrl = new URL(process.env.DATABASE_URL!);
|
||||
|
||||
const m = new Memory({
|
||||
vectorStore: {
|
||||
provider: "pgvector",
|
||||
config: {
|
||||
user: decodeURIComponent(databaseUrl.username),
|
||||
password: decodeURIComponent(databaseUrl.password),
|
||||
host: databaseUrl.hostname,
|
||||
port: Number(databaseUrl.port || 5432),
|
||||
dbname: databaseUrl.pathname.slice(1) || "neondb",
|
||||
connectionString: process.env.DATABASE_URL!,
|
||||
ssl: {
|
||||
rejectUnauthorized: false,
|
||||
},
|
||||
collectionName: "memories",
|
||||
dimension: 1536,
|
||||
embeddingModelDims: 1536,
|
||||
@@ -90,6 +87,7 @@ const results = await m.search("What movies should I recommend?", {
|
||||
|
||||
console.log(results);
|
||||
```
|
||||
|
||||
</CodeGroup>
|
||||
|
||||
## SQL Migration
|
||||
@@ -116,20 +114,19 @@ DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neond
|
||||
| `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |
|
||||
</Tab>
|
||||
<Tab title="TypeScript">
|
||||
The current Mem0 TypeScript `pgvector` adapter takes individual Postgres fields,
|
||||
so parse `DATABASE_URL` before creating `Memory`.
|
||||
Use the Neon `DATABASE_URL` directly with `connectionString`. Set `ssl` if your runtime needs an explicit TLS config object.
|
||||
|
||||
| Parameter | Description | Default |
|
||||
| -------------------- | ---------------------------------------------- | -------------- |
|
||||
| `connectionString` | Neon Postgres connection string. | Required |
|
||||
| `ssl` | Optional TLS settings passed directly to `pg`. | Driver default |
|
||||
| `collectionName` | Name for the vector collection. | `memories` |
|
||||
| `dimension` | Vector dimension for Mem0 config. | Auto-detected |
|
||||
| `embeddingModelDims` | Embedding model dimensions for table creation. | Required |
|
||||
| `hnsw` | Enables HNSW indexing. | `false` |
|
||||
|
||||
**TLS note:** `ssl: true` is sufficient for most Neon connections since Neon uses valid certificates. Use `ssl: { rejectUnauthorized: false }` only when connecting through Neon's connection pooler on certain edge runtimes (e.g. Cloudflare Workers) that require it, or when your environment does not trust the Neon CA chain.
|
||||
|
||||
| Parameter | Description | Default |
|
||||
| --- | --- | --- |
|
||||
| `user` | Database user. | Required |
|
||||
| `password` | Database password. | Required |
|
||||
| `host` | Database host. | Required |
|
||||
| `port` | Database port. | `5432` |
|
||||
| `dbname` | Database name. | `vector_store` |
|
||||
| `collectionName` | Name for the vector collection. | `memories` |
|
||||
| `dimension` | Vector dimension for Mem0 config. | Auto-detected |
|
||||
| `embeddingModelDims` | Embedding model dimensions for table creation. | Required |
|
||||
| `hnsw` | Enables HNSW indexing. | `false` |
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@ description: "Use AWS Neptune Analytics as a vector store in Mem0, combining gra
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install mem0ai[vector_stores]
|
||||
pip install mem0ai[vector-stores]
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
title: "pgvector"
|
||||
description: "Use pgvector as a vector store in Mem0 for PostgreSQL-based vector similarity search with open-source simplicity."
|
||||
---
|
||||
|
||||
[pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
|
||||
|
||||
### Usage
|
||||
@@ -21,7 +22,7 @@ config = {
|
||||
"password": "123",
|
||||
"host": "127.0.0.1",
|
||||
"port": "5432",
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -30,25 +31,22 @@ messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about 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": "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';
|
||||
import { Memory } from "mem0ai/oss";
|
||||
|
||||
const config = {
|
||||
vectorStore: {
|
||||
provider: 'pgvector',
|
||||
provider: "pgvector",
|
||||
config: {
|
||||
collectionName: 'memories',
|
||||
collectionName: "memories",
|
||||
embeddingModelDims: 1536,
|
||||
user: 'test',
|
||||
password: '123',
|
||||
host: '127.0.0.1',
|
||||
port: 5432,
|
||||
dbname: 'vector_store', // Optional; TypeScript OSS defaults to `vector_store` when omitted
|
||||
connectionString: "postgresql://test:123@localhost:5432/vector_store",
|
||||
diskann: false, // Optional, requires pgvectorscale extension
|
||||
hnsw: false, // Optional, for HNSW indexing
|
||||
},
|
||||
@@ -57,37 +55,44 @@ const config = {
|
||||
|
||||
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 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 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>
|
||||
|
||||
### Config
|
||||
|
||||
Here are the parameters available for configuring pgvector:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
| `dbname` | The name of the database | `postgres` |
|
||||
| `collection_name` | The name of the collection | `mem0` |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||||
| `user` | User name to connect to the database | `None` |
|
||||
| `password` | Password to connect to the database | `None` |
|
||||
| `host` | The host where the Postgres server is running | `None` |
|
||||
| `port` | The port where the Postgres server is running | `None` |
|
||||
| `diskann` | Whether to use diskann for vector similarity search (requires pgvectorscale) | `True` |
|
||||
| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
|
||||
| `sslmode` | SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') | `None` |
|
||||
| `connection_string` | PostgreSQL connection string (overrides individual connection parameters) | `None` |
|
||||
| `connection_pool` | psycopg2 connection pool object (overrides connection string and individual parameters) | `None` |
|
||||
| Parameter | SDK | Description | Default Value |
|
||||
| -------------------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
|
||||
| `connectionString` | TypeScript OSS | PostgreSQL connection string for direct connections. When set, Mem0 connects to the target database directly and skips the bootstrap `postgres` database flow. | `None` |
|
||||
| `ssl` | TypeScript OSS | SSL option passed directly to `pg`, either `true` or an SSL config object, for both `connectionString` and split-field connections. | `None` |
|
||||
| `dbname` | TypeScript OSS | Split-field database name. This is only used when `connectionString` is absent. | `vector_store` |
|
||||
| `collectionName` | TypeScript OSS | Collection name. | `memories` |
|
||||
| `embeddingModelDims` | TypeScript OSS | Dimensions of the embedding model. | Required |
|
||||
| `user` | TypeScript OSS + Python | Database user for split-field connections. | `None` |
|
||||
| `password` | TypeScript OSS + Python | Database password for split-field connections. | `None` |
|
||||
| `host` | TypeScript OSS + Python | Database host for split-field connections. | `None` |
|
||||
| `port` | TypeScript OSS + Python | Database port for split-field connections. | `None` |
|
||||
| `diskann` | TypeScript OSS + Python | Whether to use DiskANN for vector similarity search, requires pgvectorscale. | `False` |
|
||||
| `hnsw` | TypeScript OSS + Python | Whether to use HNSW for vector similarity search. | TypeScript OSS: `False`, Python: `True` |
|
||||
| `connection_string` | Python only | PostgreSQL connection string, overrides individual connection parameters. | `None` |
|
||||
| `sslmode` | Python only | SSL mode for PostgreSQL connections, such as `require`, `prefer`, or `disable`. | `None` |
|
||||
| `connection_pool` | Python only | psycopg connection pool object, overrides connection string and individual connection parameters. | `None` |
|
||||
|
||||
**Note (TypeScript OSS):** If you omit `dbname`, the TypeScript client uses the database name `vector_store`. Python defaults to `postgres` for `dbname`, as in the table above.
|
||||
**TypeScript OSS:** Use `connectionString` plus optional `ssl` for managed Postgres setups. If you omit `connectionString`, Mem0 falls back to split fields and uses `dbname`, `user`, `password`, `host`, `port`, and optional `ssl`.
|
||||
|
||||
**Python:** The Python SDK uses snake_case keys such as `connection_string`, `sslmode`, `collection_name`, and `embedding_model_dims`.
|
||||
|
||||
**Python connection priority**:
|
||||
|
||||
**Note**: The connection parameters have the following priority:
|
||||
1. `connection_pool` (highest priority)
|
||||
2. `connection_string`
|
||||
3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)
|
||||
3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)
|
||||
|
||||
@@ -18,7 +18,9 @@ os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
|
||||
config = {
|
||||
"vector_store": {
|
||||
"provider": "upstash_vector",
|
||||
"enable_embeddings": True,
|
||||
"config": {
|
||||
"enable_embeddings": True,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ description: "Use Valkey as an open-source vector store in Mem0 for high-perform
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install mem0ai[vector_stores]
|
||||
pip install mem0ai[vector-stores]
|
||||
```
|
||||
|
||||
## Usage
|
||||
@@ -51,7 +51,7 @@ Here are the parameters available for configuring Valkey:
|
||||
| `hnsw_ef_construction` | Size of dynamic candidate list for HNSW | `200` |
|
||||
| `hnsw_ef_runtime` | Size of dynamic candidate list for search | `10` |
|
||||
| `cluster_mode` | Enable cluster mode for Valkey cluster (CME) deployments | `false` |
|
||||
| `distance_metric` | Distance metric for vector similarity | `cosine` |
|
||||
| `timezone` | Timezone for timestamp handling | `UTC` |
|
||||
|
||||
## Cluster Mode
|
||||
|
||||
|
||||
@@ -24,7 +24,7 @@ config = {
|
||||
"deployment_index_id": "YOUR_DEPLOYMENT_INDEX_ID", # Required: Deployment-specific ID
|
||||
"project_id": "YOUR_PROJECT_ID", # Required: Google Cloud project ID
|
||||
"project_number": "YOUR_PROJECT_NUMBER", # Required: Google Cloud project number
|
||||
"region": "YOUR_REGION", # Optional: Defaults to GOOGLE_CLOUD_REGION
|
||||
"region": "YOUR_REGION", # Required: Google Cloud region
|
||||
"credentials_path": "path/to/credentials.json", # Optional: Defaults to GOOGLE_APPLICATION_CREDENTIALS
|
||||
"vector_search_api_endpoint": "YOUR_API_ENDPOINT" # Required for get operations
|
||||
}
|
||||
@@ -45,5 +45,6 @@ m.add("Your text here", user_id="user", metadata={"category": "example"})
|
||||
| `project_id` | Google Cloud project ID | Yes |
|
||||
| `project_number` | Google Cloud project number | Yes |
|
||||
| `vector_search_api_endpoint` | Vector search API endpoint | Yes (for get operations) |
|
||||
| `region` | Google Cloud region | No (defaults to GOOGLE_CLOUD_REGION) |
|
||||
| `region` | Google Cloud region | Yes |
|
||||
| `credentials_path` | Path to service account credentials | No (defaults to GOOGLE_APPLICATION_CREDENTIALS) |
|
||||
| `service_account_json` | Service account credentials as a dictionary (alternative to `credentials_path`) | `None` |
|
||||
|
||||
@@ -7,7 +7,7 @@ description: "Use Weaviate as an open-source vector search engine in Mem0 for st
|
||||
|
||||
### Installation
|
||||
```bash
|
||||
pip install weaviate weaviate-client
|
||||
pip install weaviate-client
|
||||
```
|
||||
|
||||
### Usage
|
||||
@@ -48,4 +48,5 @@ Here are the parameters available for configuring Weaviate:
|
||||
| `collection_name` | The name of the collection to store the vectors | `mem0` |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||||
| `cluster_url` | URL for the Weaviate server | `None` |
|
||||
| `auth_client_secret` | API key for Weaviate authentication | `None` |
|
||||
| `auth_client_secret` | API key for Weaviate authentication | `None` |
|
||||
| `additional_headers` | Additional headers to include in requests (`Dict[str, str]`) | `None` |
|
||||
@@ -10,7 +10,7 @@ Mem0 includes built-in support for various popular databases. Memory can utilize
|
||||
See the list of supported vector databases below.
|
||||
|
||||
<Note>
|
||||
The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis, Valkey, Vectorize and in-memory vector database.
|
||||
The following vector databases are supported in the Python implementation. The TypeScript implementation currently supports Qdrant, Redis, PGVector, Supabase, LangChain, Azure AI Search, Vectorize, and an in-memory store.
|
||||
</Note>
|
||||
|
||||
<CardGroup cols={3}>
|
||||
|
||||
Reference in New Issue
Block a user