klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add support for Mem0 REST API Server in OSS package (#2240)

Browse Source
This commit is contained in:
Deshraj Yadav
2025-02-21 01:05:55 -08:00
committed by GitHub
parent 3db028c719
commit 244fd2231d
18 changed files with 433 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/api-reference/memory/v1-get-memories.mdx
View File

@@ -1,4 +1,4 @@
---
title: 'V1 Get Memories'
title: 'Get Memories (v1 - Deprecated)'
openapi: get /v1/memories/
---

2
docs/api-reference/memory/v1-search-memories.mdx
View File

@@ -1,4 +1,4 @@
---
title: 'V1 Search Memories'
title: 'Search Memories (v1 - Deprecated)'
openapi: post /v1/memories/search/
---

69
docs/api-reference/memory/v2-get-memories.mdx
View File

@@ -1,58 +1,35 @@
---
title: 'V2 Get Memories'
title: 'Get Memories (v2)'
openapi: post /v2/memories/
---
The v2 get memories API is powerful and flexible, allowing for more precise memory listing without the need for a search query. It supports complex logical operations (AND, OR) and comparison operators for advanced filtering capabilities. The comparison operators include:
- `in`: Matches any of the values specified
- `gte`: Greater than or equal to
- `lte`: Less than or equal to
- `gt`: Greater than
- `lt`: Less than
Mem0 offers two versions of the get memories API: v1 and v2. Here's how they differ:
<Tabs>
<Tab title="v1 Get Memories">
<CodeGroup>
```python Code
memories = m.get_all(user_id="alex")
```
```json Output
[
{
"id":"f38b689d-6b24-45b7-bced-17fbb4d8bac7",
"memory":"travelling to Paris",
"user_id":"alex",
"hash":"62bc074f56d1f909f1b4c2b639f56f6a",
"metadata":null,
"created_at":"2023-02-25T23:57:00.108347-07:00",
"updated_at":"2024-07-25T23:57:00.108367-07:00"
}
]
```
</CodeGroup>
</Tab>
<Tab title="v2 Get Memories">
<CodeGroup>
```python Code
memories = m.get_all(
<CodeGroup>
```python Code
memories = m.get_all(
filters={
"AND": [
{
"user_id": "alex"
},
{
"created_at": {
"gte": "2024-07-01",
"lte": "2024-07-31"
}
"created_at": {"gte": "2024-07-01", "lte": "2024-07-31"}
}
]
},
version="v2"
)
```
)
```
```json Output
[
{
```json Output
[
{
"id":"f38b689d-6b24-45b7-bced-17fbb4d8bac7",
"memory":"Name: Alex. Vegetarian. Allergic to nuts.",
"user_id":"alex",
@@ -60,15 +37,7 @@ Mem0 offers two versions of the get memories API: v1 and v2. Here's how they dif
"metadata":null,
"created_at":"2024-07-25T23:57:00.108347-07:00",
"updated_at":"2024-07-25T23:57:00.108367-07:00"
}
}
]
```
</CodeGroup>
</Tab>
</Tabs>
Key difference between v1 and v2 get memories:
• **Filters**: v2 allows you to apply filters to narrow down memory retrieval based on specific criteria. This includes support for complex logical operations (AND, OR) and comparison operators (IN, gte, lte, gt, lt, ne, icontains) for advanced filtering capabilities.
The v2 get memories API is more powerful and flexible, allowing for more precise memory retrieval without the need for a search query.
```
</CodeGroup>

60
docs/api-reference/memory/v2-search-memories.mdx
View File

@@ -1,56 +1,32 @@
---
title: 'V2 Search Memories'
title: 'Search Memories (v2)'
openapi: post /v2/memories/search/
---
Mem0 offers two versions of the search API: v1 and v2. Here's how they differ:
The v2 search API is powerful and flexible, allowing for more precise memory retrieval. It supports complex logical operations (AND, OR) and comparison operators for advanced filtering capabilities. The comparison operators include:
- `in`: Matches any of the values specified
- `gte`: Greater than or equal to
- `lte`: Less than or equal to
- `gt`: Greater than
- `lt`: Less than
- `ne`: Not equal to
- `icontains`: Case-insensitive containment check
<Tabs>
<Tab title="v1 Search">
<CodeGroup>
```python Code
related_memories = m.search(query="What are Alice's hobbies?", user_id="alice")
```
```json Output
[
{
"id":"ea925981-272f-40dd-b576-be64e4871429",
"memory":"Likes to play cricket and plays cricket on weekends.",
"metadata":{
"category":"hobbies"
},
"score":0.32116443111457704,
"created_at":"2024-07-26T10:29:36.630547-07:00",
"updated_at":"None",
"user_id":"alice"
}
]
```
</CodeGroup>
</Tab>
<Tab title="v2 Search">
<CodeGroup>
```python Code
related_memories = m.vsearch(
query="What are Alice's hobbies?",
version="v2",
filters={
"AND":[
"AND": [
{
"user_id":"alice"
"user_id": "alice"
},
{
"agent_id":{
"in":[
"travelling",
"sports"
]
}
"agent_id": {"in": ["travel-agent", "sports-agent"]}
}
]
},
version="v2"
)
```
@@ -67,17 +43,9 @@ Mem0 offers two versions of the search API: v1 and v2. Here's how they differ:
"created_at": "2024-07-26T10:29:36.630547-07:00",
"updated_at": null,
"user_id": "alice",
"agent_id": "sports"
"agent_id": "sports-agent"
}
],
}
```
</CodeGroup>
</Tab>
</Tabs>
Key difference between v1 and v2 search:
• **Filters**: v2 allows you to apply filters to narrow down search results based on specific criteria. This includes support for complex logical operations (AND, OR) and comparison operators (IN, gte, lte, gt, lt, ne, icontains) for advanced filtering capabilities.
The v2 search API is more powerful and flexible, allowing for more precise memory retrieval.

24
docs/api-reference/overview.mdx
View File

@@ -38,28 +38,26 @@ Organizations and projects provide the following capabilities:
Example with the mem0 Python package:
<Tabs>
<Tab title="Python">
```python
from mem0 import MemoryClient
# Recommended: Using organization and project IDs
client = MemoryClient(
org_id='YOUR_ORG_ID', # It can be found on the organization settings page in dashboard
project_id='YOUR_PROJECT_ID',
)
client = MemoryClient(org_id='YOUR_ORG_ID', project_id='YOUR_PROJECT_ID')
```
Example with the mem0 Node.js package:
</Tab>
<Tab title="Node.js">
```javascript
import { MemoryClient } from "mem0ai";
# Recommended: Using organization and project IDs
const client = new MemoryClient({
organizationId: "YOUR_ORG_ID",
projectId: "YOUR_PROJECT_ID"
});
const client = new MemoryClient({organizationId: "YOUR_ORG_ID", projectId: "YOUR_PROJECT_ID"});
```
</Tab>
</Tabs>
## Getting Started
To begin using the Mem0 API, you'll need to:

26
docs/docs.json
View File

@@ -70,7 +70,8 @@
"pages": [
"features/openai_compatibility",
"features/custom-prompts",
"open-source/multimodal-support"
"open-source/multimodal-support",
"open-source/features/rest-api"
]
},
{
@@ -201,18 +202,18 @@
"group": "Memory APIs",
"icon": "microchip",
"pages": [
"api-reference/memory/v1-get-memories",
"api-reference/memory/v2-get-memories",
"api-reference/memory/add-memories",
"api-reference/memory/delete-memories",
"api-reference/memory/v2-search-memories",
"api-reference/memory/v1-search-memories",
"api-reference/memory/v2-get-memories",
"api-reference/memory/v1-get-memories",
"api-reference/memory/history-memory",
"api-reference/memory/get-memory",
"api-reference/memory/update-memory",
"api-reference/memory/delete-memory",
"api-reference/memory/v1-search-memories",
"api-reference/memory/v2-search-memories",
"api-reference/memory/history-memory",
"api-reference/memory/batch-update",
"api-reference/memory/delete-memory",
"api-reference/memory/batch-delete",
"api-reference/memory/delete-memories",
"api-reference/memory/create-memory-export",
"api-reference/memory/get-memory-export"
]
@@ -229,17 +230,12 @@
"group": "Organizations APIs",
"icon": "building",
"pages": [
"api-reference/organization/create-org",
"api-reference/organization/get-orgs",
"api-reference/organization/get-org",
"api-reference/organization/create-org",
"api-reference/organization/update-org",
"api-reference/organization/delete-org",
"api-reference/organization/get-org-members",
"api-reference/organization/add-org-member",
"api-reference/organization/remove-org-member",
"api-reference/organization/get-org-projects",
"api-reference/organization/add-org-project",
"api-reference/organization/remove-org-project"
"api-reference/organization/delete-org"
]
}
]

BIN
docs/images/ai-assistant.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 2.8 MiB

BIN
docs/images/ai-tutor.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 843 KiB

BIN
docs/images/customer-support-agent.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 4.6 MiB

BIN
docs/images/personal-travel-agent.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 3.9 MiB

BIN
docs/images/rest-api-server.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 110 KiB

77
docs/open-source/features/rest-api.mdx Normal file
View File

@@ -0,0 +1,77 @@
---
title: REST API Server
icon: "server"
iconType: "solid"
---
Mem0 provides a REST API server (written using FastAPI). Users can perform all operations through REST endpoints. The API also includes OpenAPI documentation, accessible at `/docs` when the server is running.
<Frame caption="APIs supported by Mem0 REST API Server">
<img src="/images/rest-api-server.png" />
</Frame>
## Features
- **Create memories:** Create memories based on messages for a user, agent, or run.
- **Retrieve memories:** Get all memories for a given user, agent, or run.
- **Search memories:** Search stored memories based on a query.
- **Update memories:** Update an existing memory.
- **Delete memories:** Delete a specific memory or all memories for a user, agent, or run.
- **Reset memories:** Reset all memories for a user, agent, or run.
- **OpenAPI Documentation:** Accessible via `/docs` endpoint.
## Running Locally
<Tabs>
<Tab title="With Docker">
1. Create a `.env` file in the current directory and set your environment variables. For example:
```txt
OPENAI_API_KEY=your-openai-api-key
```
2. Build the Docker image:
```bash
docker build -t mem0-api-server .
```
3. Run the Docker container:
``` bash
docker run -p 8000:8000 mem0-api-server
```
4. Access the API at http://localhost:8000.
</Tab>
<Tab title="Without Docker">
1. Create a `.env` file in the current directory and set your environment variables. For example:
```txt
OPENAI_API_KEY=your-openai-api-key
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Start the FastAPI server:
```bash
uvicorn main:app --reload
```
4. Access the API at http://localhost:8000.
</Tab>
</Tabs>
## Usage
Once the server is running (locally or via Docker), you can interact with it using any REST client or through your preferred programming language (e.g., Go, Java, etc.). You can test out the APIs using the OpenAPI documentation at [http://localhost:8000/docs](http://localhost:8000/docs) endpoint.

2
docs/platform/quickstart.mdx
View File

@@ -1156,7 +1156,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&keywords=to play&p
#### Get all memories using custom filters
Our advanced retrieval allows you to set custom filters when fetching memories. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and keywords. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains). For more details, see [V2 Get Memories](/api-reference/memory/v2-get-memories).
Our advanced retrieval allows you to set custom filters when fetching memories. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and keywords. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains). For more details, see [v2 Get Memories](/api-reference/memory/v2-get-memories).
Here you need to define `version` as `v2` in the get_all method.

16
server/Dockerfile Normal file
View File

@@ -0,0 +1,16 @@
FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY .env .
COPY . .
EXPOSE 8000
ENV PYTHONUNBUFFERED=1
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

7
server/Makefile Normal file
View File

@@ -0,0 +1,7 @@
build:
docker build -t mem0-api-server .
run_local:
docker run -p 8000:8000 -v $(shell pwd):/app mem0-api-server
.PHONY: build run_local

63
server/README.md Normal file
View File

@@ -0,0 +1,63 @@
# Mem0 REST API Server
Mem0 provides a REST API server (written using FastAPI). Users can perform all operations through REST endpoints. The API also includes OpenAPI documentation, accessible at `/docs` when the server is running.
## Features
- **Create memories:** Create memories based on messages for a user, agent, or run.
- **Retrieve memories:** Get all memories for a given user, agent, or run.
- **Search memories:** Search stored memories based on a query.
- **Update memories:** Update an existing memory.
- **Delete memories:** Delete a specific memory or all memories for a user, agent, or run.
- **Reset memories:** Reset all memories for a user, agent, or run.
- **OpenAPI Documentation:** Accessible via `/docs` endpoint.
## Running Locally
### With Docker
1. Create a `.env` file in the root directory of the project and set your environment variables. For example:
```env
OPENAI_API_KEY=your-openai-api-key
```
2. Build the Docker image:
```bash
docker build -t mem0-api-server .
```
3. Run the Docker container:
``` bash
docker run -p 8000:8000 mem0-api-server
```
4. Access the API at http://localhost:8000.
### Without Docker
1. Create a `.env` file in the root directory of the project and set your environment variables. For example:
```env
OPENAI_API_KEY=your-openai-api-key
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Start the FastAPI server:
```bash
uvicorn main:app --reload
```
4. Access the API at http://localhost:8000.
### Usage
Once the server is running (locally or via Docker), you can interact with it using any REST client or through your preferred programming language (e.g., Go, Java, etc.). You can test out the APIs using the OpenAPI documentation at [`http://localhost:8000/docs`](http://localhost:8000/docs) endpoint.

158
server/main.py Normal file
View File

@@ -0,0 +1,158 @@
import os
from fastapi import FastAPI, HTTPException, Query, Path
from fastapi.responses import JSONResponse, RedirectResponse
from pydantic import BaseModel, Field
from typing import Optional, List, Any, Dict
from mem0 import Memory
from dotenv import load_dotenv
# Load environment variables
load_dotenv()
MEMORY_INSTANCE = Memory()
app = FastAPI(
title="Mem0 REST APIs",
description="A REST API for managing and searching memories for your AI Agents and Apps.",
version="1.0.0",
)
class Message(BaseModel):
role: str = Field(..., description="Role of the message (user or assistant).")
content: str = Field(..., description="Message content.")
class MemoryCreate(BaseModel):
messages: List[Message] = Field(..., description="List of messages to store.")
user_id: Optional[str] = None
agent_id: Optional[str] = None
run_id: Optional[str] = None
metadata: Optional[Dict[str, Any]] = None
class SearchRequest(BaseModel):
query: str = Field(..., description="Search query.")
user_id: Optional[str] = None
run_id: Optional[str] = None
agent_id: Optional[str] = None
@app.post("/configure", summary="Configure Mem0")
def set_config(config: Dict[str, Any]):
"""Set memory configuration."""
global MEMORY_INSTANCE
MEMORY_INSTANCE = Memory.from_config(config)
return {"message": "Configuration set successfully"}
@app.post("/memories", summary="Create memories")
def add_memory(memory_create: MemoryCreate):
"""Store new memories."""
if not any([memory_create.user_id, memory_create.agent_id, memory_create.run_id]):
raise HTTPException(
status_code=400, detail="At least one identifier (user_id, agent_id, run_id) is required."
)
params = {k: v for k, v in memory_create.model_dump().items() if v is not None and k != "messages"}
try:
response = MEMORY_INSTANCE.add(messages=[m.model_dump() for m in memory_create.messages], **params)
return JSONResponse(content=response)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.get("/memories", summary="Get memories")
def get_all_memories(
user_id: Optional[str] = None,
run_id: Optional[str] = None,
agent_id: Optional[str] = None,
):
"""Retrieve stored memories."""
if not any([user_id, run_id, agent_id]):
raise HTTPException(status_code=400, detail="At least one identifier is required.")
try:
params = {k: v for k, v in {"user_id": user_id, "run_id": run_id, "agent_id": agent_id}.items() if v is not None}
return MEMORY_INSTANCE.get_all(**params)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.get("/memories/{memory_id}", summary="Get a memory")
def get_memory(memory_id: str):
"""Retrieve a specific memory by ID."""
try:
return MEMORY_INSTANCE.get(memory_id)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.post("/search", summary="Search memories")
def search_memories(search_req: SearchRequest):
"""Search for memories based on a query."""
try:
params = {k: v for k, v in search_req.model_dump().items() if v is not None and k != "query"}
return MEMORY_INSTANCE.search(query=search_req.query, **params)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.put("/memories/{memory_id}", summary="Update a memory")
def update_memory(memory_id: str, updated_memory: Dict[str, Any]):
"""Update an existing memory."""
try:
return MEMORY_INSTANCE.update(memory_id=memory_id, data=updated_memory)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.get("/memories/{memory_id}/history", summary="Get memory history")
def memory_history(memory_id: str):
"""Retrieve memory history."""
try:
return MEMORY_INSTANCE.history(memory_id=memory_id)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.delete("/memories/{memory_id}", summary="Delete a memory")
def delete_memory(memory_id: str):
"""Delete a specific memory by ID."""
try:
MEMORY_INSTANCE.delete(memory_id=memory_id)
return {"message": "Memory deleted successfully"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.delete("/memories", summary="Delete all memories")
def delete_all_memories(
user_id: Optional[str] = None,
run_id: Optional[str] = None,
agent_id: Optional[str] = None,
):
"""Delete all memories for a given identifier."""
if not any([user_id, run_id, agent_id]):
raise HTTPException(status_code=400, detail="At least one identifier is required.")
try:
params = {k: v for k, v in {"user_id": user_id, "run_id": run_id, "agent_id": agent_id}.items() if v is not None}
MEMORY_INSTANCE.delete_all(**params)
return {"message": "All relevant memories deleted"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.post("/reset", summary="Reset all memories")
def reset_memory():
"""Completely reset stored memories."""
try:
MEMORY_INSTANCE.reset()
return {"message": "All memories reset"}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.get("/", summary="Redirect to the OpenAPI documentation", include_in_schema=False)
def home():
"""Redirect to the OpenAPI documentation."""
return RedirectResponse(url='/docs')

5
server/requirements.txt Normal file
View File

@@ -0,0 +1,5 @@
fastapi==0.115.8
uvicorn==0.34.0
pydantic==2.10.4
mem0ai>=0.1.48
python-dotenv==1.0.1