mirror of
https://github.com/rowboatlabs/rowboat.git
synced 2026-04-25 00:16:29 +02:00
Add support for RAG
This commit is contained in:
parent
2156c94449
commit
b80eaffbe9
22 changed files with 552 additions and 900 deletions
92
apps/docs/docs/using_rag.md
Normal file
92
apps/docs/docs/using_rag.md
Normal file
|
|
@ -0,0 +1,92 @@
|
|||
# Using RAG in Rowboat
|
||||
|
||||
Rowboat provides multiple ways to enhance your agents with Retrieval-Augmented Generation (RAG). This guide will help you set up and use each RAG feature.
|
||||
|
||||
## Quick Start
|
||||
|
||||
Text RAG and local file uploads are enabled by default - no configuration needed! Just start using them right away.
|
||||
|
||||
## Available RAG Features
|
||||
|
||||
### 1. Text RAG
|
||||
✅ Enabled by default:
|
||||
|
||||
- Process and reason over text content directly
|
||||
- No configuration required
|
||||
|
||||
### 2. Local File Uploads
|
||||
✅ Enabled by default:
|
||||
|
||||
- Upload PDF files directly from your device
|
||||
- Files are stored locally
|
||||
- No configuration required
|
||||
- Files are parsed using OpenAI by default
|
||||
|
||||
### 3. S3 File Uploads
|
||||
To enable S3 file uploads, set the following variables:
|
||||
|
||||
```bash
|
||||
# Enable S3 uploads
|
||||
export USE_RAG_S3_UPLOADS=true
|
||||
|
||||
# S3 Configuration
|
||||
export AWS_ACCESS_KEY_ID=your_access_key
|
||||
export AWS_SECRET_ACCESS_KEY=your_secret_key
|
||||
export RAG_UPLOADS_S3_BUCKET=your_bucket_name
|
||||
export RAG_UPLOADS_S3_REGION=your_region
|
||||
```
|
||||
|
||||
### 4. URL Scraping
|
||||
To enable URL scraping, set the following variables:
|
||||
|
||||
```bash
|
||||
# Enable URL scraping
|
||||
export USE_RAG_SCRAPING=true
|
||||
|
||||
# Firecrawl API key for web scraping
|
||||
export FIRECRAWL_API_KEY=your_firecrawl_api_key
|
||||
```
|
||||
|
||||
## File Parsing Options
|
||||
|
||||
### Default Parsing (OpenAI)
|
||||
By default, uploaded PDF files are parsed using `gpt-4o`. You can customize this by setting the following:
|
||||
|
||||
```bash
|
||||
# Override the default parsing model
|
||||
export FILE_PARSING_MODEL=your-preferred-model
|
||||
```
|
||||
|
||||
You can also change the model provider like so:
|
||||
```bash
|
||||
# Optional: Override the parsing provider settings
|
||||
export FILE_PARSING_PROVIDER_BASE_URL=your-provider-base-url
|
||||
export FILE_PARSING_PROVIDER_API_KEY=your-provider-api-key
|
||||
```
|
||||
|
||||
### Using Gemini for File Parsing
|
||||
To use Google's Gemini model for parsing uploaded PDFs, set the following variable:
|
||||
|
||||
```bash
|
||||
# Enable Gemini for file parsing
|
||||
export USE_GEMINI_FILE_PARSING=true
|
||||
export GOOGLE_API_KEY=your_google_api_key
|
||||
```
|
||||
|
||||
## Embedding Model options
|
||||
|
||||
By default, Rowboat uses OpenAI's `text-embedding-3-small` model for generating embeddings. You can customize this by setting the following:
|
||||
|
||||
```bash
|
||||
# Override the default embedding model
|
||||
export EMBEDDING_MODEL=your-preferred-model
|
||||
```
|
||||
|
||||
You can also change the model provider like so:
|
||||
```bash
|
||||
# Optional: Override the embedding provider settings
|
||||
export EMBEDDING_PROVIDER_BASE_URL=your-provider-base-url
|
||||
export EMBEDDING_PROVIDER_API_KEY=your-provider-api-key
|
||||
```
|
||||
|
||||
If you don't specify the provider settings, Rowboat will use OpenAI as the default provider.
|
||||
|
|
@ -14,6 +14,7 @@ nav:
|
|||
- Test chats in the playground: playground.md
|
||||
- Add tools: add_tools.md
|
||||
- Update agents: update_agents.md
|
||||
- Using RAG: using_rag.md
|
||||
|
||||
- API & SDK:
|
||||
- Using the API: using_the_api.md
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue