Checkpoint

Author: abrookins

Dockerfile

@@ -2,15 +2,20 @@ FROM python:3.12-slim
 
 WORKDIR /app
 
-# Install dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Install system dependencies including build tools
+RUN apt-get update && apt-get install -y \
+    curl \
+    build-essential \
+    gcc \
+    g++ \
+    && rm -rf /var/lib/apt/lists/*
 
-# Copy application code
-COPY . .
+# Copy project files
+COPY pyproject.toml README.md ./
+COPY redis_memory_server ./redis_memory_server
 
-# Set environment variables
-ENV PORT=8000
+# Install Python dependencies
+RUN pip install --no-cache-dir -e .
 
-# Run the application
-CMD ["python", "main.py"]
+# Run the API server
+CMD ["python", "-m", "redis_memory_server.main"]

LICENSE.m LICENSELICENSE.m renamed to LICENSE

@@ -1,97 +1,76 @@
 # Redis Memory Server
 
-A service that provides memory management for AI applications using Redis.
+A service that provides memory management for AI applications using Redis. This server helps manage both short-term and long-term memory for AI conversations, with features like automatic topic extraction, entity recognition, and context summarization.
 
 ## Features
 
-- Short-term memory management with configurable window size
-- Long-term memory with semantic search capabilities
-- Automatic context summarization using LLMs
-- Support for multiple model providers (OpenAI and Anthropic)
-- Configurable token limits based on selected model
-- Topic extraction using BERTopic
-- Named Entity Recognition using BERT
+- **Short-term Memory Management**
+  - Configurable window size for recent messages
+  - Automatic context summarization using LLMs
+  - Token limit management based on model capabilities
 
-## Configuration
+- **Long-term Memory**
+  - Semantic search capabilities
+  - Automatic message indexing
+  - Configurable memory retention
 
-The service can be configured using environment variables:
-
-- `REDIS_URL`: URL for Redis connection (default: `redis://localhost:6379`)
-- `LONG_TERM_MEMORY`: Enable/disable long-term memory (default: `True`)
-- `WINDOW_SIZE`: Maximum number of messages to keep in short-term memory (default: `20`)
-- `OPENAI_API_KEY`: API key for OpenAI
-- `ANTHROPIC_API_KEY`: API key for Anthropic
-- `GENERATION_MODEL`: Model to use for text generation (default: `gpt-4o-mini`)
-- `EMBEDDING_MODEL`: Model to use for text embeddings (default: `text-embedding-3-small`)
-- `PORT`: Port to run the server on (default: `8000`)
-- `TOPIC_MODEL`: BERTopic model to use for topic extraction (default: `MaartenGr/BERTopic_Wikipedia`)
-- `NER_MODEL`: BERT model to use for named entity recognition (default: `dbmdz/bert-large-cased-finetuned-conll03-english`)
-- `ENABLE_TOPIC_EXTRACTION`: Enable/disable topic extraction (default: `True`)
-- `ENABLE_NER`: Enable/disable named entity recognition (default: `True`)
+- **Advanced Features**
+  - Topic extraction using BERTopic
+  - Named Entity Recognition using BERT
+  - Support for multiple model providers (OpenAI and Anthropic)
+  - Namespace support for session isolation
 
-## Supported Models
+## Get Started
 
-### OpenAI Models
+### Docker Compose
 
-- `gpt-3.5-turbo`: 4K context window
-- `gpt-3.5-turbo-16k`: 16K context window
-- `gpt-4`: 8K context window
-- `gpt-4-32k`: 32K context window
-- `gpt-4o`: 128K context window
-- `gpt-4o-mini`: 128K context window
+To start the API using Docker Compose, follow these steps:
 
-### Anthropic Models
+1. Ensure that Docker and Docker Compose are installed on your system.
 
-- `claude-3-opus-20240229`: 200K context window
-- `claude-3-sonnet-20240229`: 200K context window
-- `claude-3-haiku-20240307`: 200K context window
-- `claude-3-5-sonnet-20240620`: 200K context window
+2. Open a terminal in the project root directory (where the docker-compose.yml file is located).
 
-### Topic and NER Models
+3. (Optional) Set up your environment variables (such as OPENAI_API_KEY and ANTHROPIC_API_KEY) either in a .env file or by modifying the docker-compose.yml as needed.
 
-- Topic Extraction: Uses BERTopic with the specified model (default: Wikipedia-trained model)
-- Named Entity Recognition: Uses BERT model fine-tuned on CoNLL-03 dataset
+4. Build and start the containers by running:
+   docker-compose up --build
 
-**Note**: Embedding operations always use OpenAI models, as Anthropic does not provide embedding API.
+5. Once the containers are up, the API will be available at http://localhost:8000. You can also access the interactive API documentation at http://localhost:8000/docs.
 
-## Installation
+6. To stop the containers, press Ctrl+C in the terminal and then run:
+   docker-compose down
 
-1. Clone the repository
-2. Install dependencies: `pip install -r requirements.txt`
-3. Set up environment variables (see Configuration section)
-4. Run the server: `python main.py`
+Happy coding!
 
-## Usage
 
-### Add Messages to Memory
+## API Reference
 
-```
-POST /sessions/{session_id}/memory
-```
+### API Docs
 
-Request body:
-```json
-{
-    "messages": [
-        {
-            "role": "user",
-            "content": "Hello, how are you?"
-        }
-    ],
-    "context": "Optional context for the conversation"
-}
+API documentation is available at:  http://localhost:8000/docs.
+
+### Endpoint Preview
+
+#### List Sessions
+```http
+GET /sessions/
 ```
 
+Query Parameters:
+- `page` (int): Page number (default: 1)
+- `size` (int): Items per page (default: 10)
+- `namespace` (string, optional): Filter sessions by namespace
+
 Response:
 ```json
-{
-    "status": "ok"
-}
+[
+    "session-1",
+    "session-2"
+]
 ```
 
-### Get Memory
-
-```
+#### Get Memory
+```http
 GET /sessions/{session_id}/memory
 ```
 
@@ -111,40 +90,119 @@ Response:
 }
 ```
 
-### List Sessions
-
-```
-GET /sessions/
+#### Add Messages to Memory
+```http
+POST /sessions/{session_id}/memory
 ```
 
-Response:
+Request Body:
 ```json
-[
-    "session-1",
-    "session-2"
-]
+{
+    "messages": [
+        {
+            "role": "user",
+            "content": "Hello, how are you?"
+        }
+    ],
+    "context": "Optional context for the conversation"
+}
 ```
 
-### Delete Session
+Query Parameters:
+- `namespace` (string, optional): Namespace for the session
 
+Response:
+```json
+{
+    "status": "ok"
+}
 ```
+
+#### Delete Session
+```http
 DELETE /sessions/{session_id}/memory
 ```
 
+Query Parameters:
+- `namespace` (string, optional): Namespace for the session
+
 Response:
 ```json
 {
     "status": "ok"
 }
 ```
 
-## Development
+## Configuration
 
-To run tests:
+You can configure the service using environment variables:
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `REDIS_URL` | URL for Redis connection | `redis://localhost:6379` |
+| `LONG_TERM_MEMORY` | Enable/disable long-term memory | `True` |
+| `WINDOW_SIZE` | Maximum messages in short-term memory | `20` |
+| `OPENAI_API_KEY` | API key for OpenAI | - |
+| `ANTHROPIC_API_KEY` | API key for Anthropic | - |
+| `GENERATION_MODEL` | Model for text generation | `gpt-4o-mini` |
+| `EMBEDDING_MODEL` | Model for text embeddings | `text-embedding-3-small` |
+| `PORT` | Server port | `8000` |
+| `TOPIC_MODEL` | BERTopic model for topic extraction | `MaartenGr/BERTopic_Wikipedia` |
+| `NER_MODEL` | BERT model for NER | `dbmdz/bert-large-cased-finetuned-conll03-english` |
+| `ENABLE_TOPIC_EXTRACTION` | Enable/disable topic extraction | `True` |
+| `ENABLE_NER` | Enable/disable named entity recognition | `True` |
+
+## Supported Models
 
+### Large Language Models
+
+Redis Memory Server supports using OpenAI and Anthropic models for generation, and OpenAI models for embeddings.
+
+### Topic and NER Models
+- **Topic Extraction**: BERTopic with Wikipedia-trained model
+- **Named Entity Recognition**: BERT model fine-tuned on CoNLL-03 dataset
+
+> **Note**: Embedding operations use OpenAI models exclusively, as Anthropic does not provide an embedding API.
+
+## Installation
+
+1. Clone the repository:
+```bash
+git clone https://github.com/yourusername/redis-memory-server.git
+cd redis-memory-server
 ```
+
+2. Install dependencies:
+```bash
+pip install -e ".[dev]"
+```
+
+3. Set up environment variables (see Configuration section)
+
+4. Run the server:
+```bash
+python -m redis_memory_server
+```
+
+## Development
+
+### Running Tests
+```bash
 python -m pytest
 ```
 
+### Contributing
+1. Fork the repository
+2. Create a feature branch
+3. Commit your changes
+4. Push to the branch
+5. Create a Pull Request
+
 ## License
-TBD
+This project derives from original work from the Motorhead project:
+https://github.com/getmetal/motorhead/
+
+The original code is licensed under the Apache License 2.0:
+https://www.apache.org/licenses/LICENSE-2.0
+
+Modifications made by Redis, Inc. are also licensed under the Apache License 2.0.

README.md

@@ -0,0 +1,46 @@
+services:
+  api:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "8000:8000"
+    environment:
+      - REDIS_URL=redis://redis:6379
+      - PORT=8000
+      # Add your API keys here or use a .env file
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      # Optional configurations with defaults
+      - LONG_TERM_MEMORY=True
+      - WINDOW_SIZE=20
+      - GENERATION_MODEL=gpt-4o-mini
+      - EMBEDDING_MODEL=text-embedding-3-small
+      - ENABLE_TOPIC_EXTRACTION=True
+      - ENABLE_NER=True
+    depends_on:
+      - redis
+    volumes:
+      - ./redis_memory_server:/app/redis_memory_server
+    healthcheck:
+      test: [ "CMD", "curl", "-f", "http://localhost:8000/health" ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  redis:
+    image: redis/redis-stack:latest
+    ports:
+      - "16379:6379" # Redis port
+      - "18001:8001" # RedisInsight port
+    volumes:
+      - redis_data:/data
+    command: redis-stack-server --save 60 1 --loglevel warning
+    healthcheck:
+      test: [ "CMD", "redis-cli", "ping" ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+volumes:
+  redis_data: