+
## Obtain API key and Project ID
Generate API keys via the developer configs in your project. Copy the Project ID from the same page.
-
+
+ 
+
## API Endpoint
diff --git a/apps/docs/docs/api-sdk/using_the_sdk.mdx b/apps/docs/docs/api-sdk/using_the_sdk.mdx
new file mode 100644
index 000000000..0909224ff
--- /dev/null
+++ b/apps/docs/docs/api-sdk/using_the_sdk.mdx
@@ -0,0 +1,91 @@
+---
+title: "Using the SDK"
+description: "This is a guide on using the RowBoat Python SDK as an alternative to the [RowBoat HTTP API](/using_the_api) to power conversations with the assistant created in Studio."
+icon: "toolbox"
+---
+
+## Prerequisites
+- ``` pip install rowboat ```
+- [Deploy your assistant to production](/using_the_api/#deploy-your-assistant-to-production-on-studio)
+- [Obtain your `
+
+
+---
+
+## How You Can Contribute
+
+
+- **Tackle Open Issues**
+ Browse our [GitHub Issues](https://github.com/rowboatlabs/rowboat/issues) for tags like `good first issue`, `help wanted`, or `bug` to find a spot that fits your skillset.
+
+- **Join the Community**
+ Our [Discord](https://discord.gg/rxB8pzHxaS) is the go-to hub for brainstorming, feedback, and finding contributors for bigger efforts.
+
+- **Propose Something New**
+ Have a new tool integration idea or found a bug? Open an issue and letβs discuss it!
+
+
+---
+
+## Contribution Workflow & Best Practices
+
+Whether it's your first contribution or your fiftieth, here's what a great contribution looks like:
+
+| Step / Tip | Description |
+|-------------------------------|-----------------------------------------------------------------------------------------------|
+| **1. Fork the Repository** | Create a personal copy of [rowboatlabs/rowboat](https://github.com/rowboatlabs/rowboat) to start contributing. |
+| **2. Create a New Branch** | Use a descriptive name like `fix-tool-crash` or `feature-new-mcp`. Avoid committing to `main`. |
+| **3. Make Your Changes** | Focus your PR on a single issue or feature to keep things clean and reviewable. |
+| **4. Write Tests if Needed** | If you change logic, add relevant tests so your contribution is future-proof. |
+| **5. Run Tests & Lint Locally**| Make sure your branch passes all tests and code quality checks before pushing. |
+| **6. Document or Demo It** | Add helpful context: screenshots, example scripts, or a short video/gif to demonstrate your changes. |
+| **7. Submit a Pull Request** | Open a PR with a clear description of your changes and any context reviewers should know. |
+| **8. Collaborate on Feedback** | Our maintainers may leave comments β itβs all part of the process. Letβs improve it together. |
+| **9. Donβt Be Shy to Follow Up** | Feel free to ping the PR/issue if you're waiting on feedback. We appreciate polite nudges. |
+| **10. Celebrate the Merge!** | You just made Rowboat better. Thanks for contributing π |
+
+
+
+
+## What is RowBoat?
+**RowBoat is a state-of-art platform to build multi-agent AI systems in a visual interface, with the help of a copilot.**
+
+RowBoat enables you to build, manage and deploy user-facing assistants. An assistant is made up of multiple agents, each having access to a set of tools and working together to interact with the user as a single assistant. You can connect any tool to the agents.
+
+For example, you can build a *meeting prep assistant* that helps you prepare for upcoming meetings. One agent can access your Google Calendar to see your scheduled meetings, another agent can research the meeting attendees (such as finding their LinkedIn profiles or recent news), and a third agent can compile this research and send it to your email before the meeting. This way, you get automated, personalized meeting prep without manual effort.
+
+---
+
+## How RowBoat works
+
+### RowBoat Studio
+RowBoat Studio lets you create AI agents in minutes, using a visual interface and plain language.
+There are key components that you will work with:
+- Agents
+- Playground
+- Copilot
+
+
+- -2. Once in Studio, create a new blank project or use one of the example templates: - -
- -3. Use the copilot to help you build agents: - -
- -4. Ensure that the correct agent is set as the "start agent": - -
- -5. Test out a chat in the playground to verify the agents' behavior: - -
- -### Testing the Chat API - -You can use the API directly at [http://localhost:3000/api/v1/](http://localhost:3000/api/v1/) -- Project ID is available in the URL of the project page -- API Key can be generated from the project config page at `/projects/
performs tasks using tools, based on instructions |β’ Configurable using plain language instructions
β’ Orchestrate between agents connected as a graph
β’ Can access tools and knowledge sources (RAG)| -| Playground | Interactive environment to test assistants
conversationally as you build them |β’ Real-time testing and debugging
β’ Inspect parameters and results of tool calls in-line
β’ Converse with individual agents or the entire assistant| -| Copilot | AI-powered concierge that creates and
updates agents and tools on your behalf |β’ Context-aware of all components including playground
β’ Improves agents based on conversations and feedback
β’ Understands your requests in plain language| - -### RowBoat Chat API & SDK -- [RowBoat Chat API](/using_the_api) is a stateless HTTP API to interface with the assistant created on RowBoat Studio. You can use the API to drive end-user facing conversations in your app or website. -- [RowBoat Chat SDK](/using_the_sdk) is a simple SDK (currently available in Python) which wraps the HTTP API under the hood. It offers both stateful and stateless (OpenAI-style) implementations. - -### Steps -**RowBoat Studio:** - -1. Describe the assistant you are looking to build, to **copilot** -2. Review and apply the **agents** (and tools) created by copilot -3. Configure **MCP servers** and **tools** and connect them to agents -4. Chat with your assistant in the **playground** -6. Deploy and use the HTTP API or Python SDK to integrate the agents into your system - -## Why RowBoat? -Rowboat is the fastest way to build and deploy MCP connected multi-agents - -1. **Build** complex assistants using plain language and a visual interface -2. **Integrate** tools and MCP servers in minutes -3. **Expedite** your multi-agent AI roadmap using battle-tested tooling - -## Getting started - -- To set up our open-source installation, see [Github Readme](https://github.com/rowboatlabs/rowboat) -- To sign up for our managed offering (beta), please email us at [founders@rowboatlabs.com](mailto:founders@rowboatlabs.com) \ No newline at end of file diff --git a/apps/docs/docs/oss_installation.md b/apps/docs/docs/oss_installation.md deleted file mode 100644 index b26c53884..000000000 --- a/apps/docs/docs/oss_installation.md +++ /dev/null @@ -1,32 +0,0 @@ -# Open Source Installation - -- This is the developers guide to self-hosting the open-source version of RowBoat. To get started with the hosted app, please see [Using the Hosted App](/hosted_setup) -- Please see our [Introduction](/) page before referring to this guide. -- For direct installation steps, please head to the README of RowBoat's Github repo: [@rowboatlabs/rowboat](https://github.com/rowboatlabs/rowboat/). This page provides more context about the installation process and the different components involved. - -## Overview - -RowBoat's codebase has three main components: - -| Component | Description | -|--------------|---------------| -| **Agents** | Python framework responsible for carrying out multi-agent conversations | -| **Copilot** | Python framework powering the copilot in RowBoat Studio | -| **RowBoat** | Frontend and backend services to power RowBoat Studio and Chat APIs | - -These components are structured as separate services, each containerized with Docker. Running `docker-compose up --build` enables you to use the Studio in your browser, as well as stands up the APIs and SDK. - -## Prerequisites -All of these prerequisites have open-source or free versions. - -| Prerequisite | Description | -|--------------|---------------| -| **Docker** | Bundles and builds all services | -| **OpenAI API Key** | Agents and Copilot services are powered by OpenAI LLMs | -| **MongoDB** | Stores workflow versions, chats and RAG embeddings | - -Refer to our [Github Readme for Prerequisites](https://github.com/rowboatlabs/rowboat/?tab=readme-ov-file#prerequisites) to set up prerequisites. - -## Setting up - -Refer to our [Github Readme for Local Development](https://github.com/rowboatlabs/rowboat/?tab=readme-ov-file#local-development-setup) to set up Studio, Chat API and SDK via `docker-compose`. \ No newline at end of file diff --git a/apps/docs/docs/playground.md b/apps/docs/docs/playground.md deleted file mode 100644 index 3f1f0590c..000000000 --- a/apps/docs/docs/playground.md +++ /dev/null @@ -1,7 +0,0 @@ -## Try an example chat in the playground - -### Chat with the assistant - -The playground is intended to test out the assistant as you build it. The User and Assistant messages represent the conversation that your end-user will have if your assistant is deployed in production. The playground also has debug elements which show the flow of control between different agents in your system, as well as which agent finally responded to the user. - - \ No newline at end of file diff --git a/apps/docs/docs/prompts.md b/apps/docs/docs/prompts.md deleted file mode 100644 index 2552cc49f..000000000 --- a/apps/docs/docs/prompts.md +++ /dev/null @@ -1,5 +0,0 @@ -# Prompts - -- Prompts are reusable pieces of agent instructions in Studio. -- Prompts can be defined once and reused across multiple agents. -- Common examples of prompts are style prompts which indicate brand voice and structured output prompts which specify a format for the agent to provide its output in (e.g. ReAct) \ No newline at end of file diff --git a/apps/docs/docs/setup.md b/apps/docs/docs/setup.md deleted file mode 100644 index f9ed3ef76..000000000 --- a/apps/docs/docs/setup.md +++ /dev/null @@ -1,127 +0,0 @@ -## Getting started - -- β¨ **Start from an idea β Copilot builds your multi-agent workflows** - E.g. "Build me an assistant for a food delivery company to handle delivery status and missing items. Include the necessary tools." -- π **Connect MCP servers** - Add the MCP servers in Settings β import the tools into Rowboat. -- π **Integrate into your app using the HTTP API or Python SDK** - Grab the Project ID and generated API Key from Settings and use the API. - -Powered by OpenAI's Agents SDK, Rowboat is the fastest way to build multi-agents! - -## Quick start - -Step 1. Set your OpenAI key: - -```bash -export OPENAI_API_KEY=your-openai-api-key -``` - -Step 2. Clone the repository and start Rowboat docker - -```bash -git clone git@github.com:rowboatlabs/rowboat.git -cd rowboat -docker-compose up --build -``` - -Step 3. Access the app at [http://localhost:3000](http://localhost:3000). - -Note: See the [Using custom LLM providers](#using-custom-llm-providers) section below for using custom providers like OpenRouter and LiteLLM. - -## Demo - -#### Create a multi-agent assistant with MCP tools by chatting with Rowboat -[](https://youtu.be/YRTCw9UHRbU) - -## Integrate with Rowboat agents - -There are 2 ways to integrate with the agents you create in Rowboat - -**Option #1: HTTP API** - -You can use the API directly at [http://localhost:3000/api/v1/](http://localhost:3000/api/v1/). See [API Docs](https://docs.rowboatlabs.com/using_the_api/) for details. - -```bash -curl --location 'http://localhost:3000/api/v1/
- -Prerequisite: - -1. **Open Source Users:** Complete the [open-source installation steps](/oss_installation/) to set up RowBoat Studio. -2. **Hosted App Users:** Sign in to [https://app.rowboatlabs.com/](https://app.rowboatlabs.com/) \ No newline at end of file diff --git a/apps/docs/docs/testing.md b/apps/docs/docs/testing.md deleted file mode 100644 index 86df88be6..000000000 --- a/apps/docs/docs/testing.md +++ /dev/null @@ -1,132 +0,0 @@ -# Testing Your Setup - -## Testing Studio - -1. Once you are set up, you should be able to login to the Studio via Auth0's login options (Gmail, Github etc.). -- For the open source installation, the URL for Studio is [http://localhost:3000](http://localhost:3000) -- To use our hosted app, the URL for Studio is [https://app.rowboatlabs.com](https://app.rowboatlabs.com/) -
- -2. Once in Studio, create a new blank project or browse through one of the example projects: - -
- -3. Use the copilot to help you build agents: - -
- -4. Ensure that the correct agent is set as the "start agent": - -
- -5. Test out a chat in the playground to verify the agents' behavior: - -
- -### Testing the Chat API - -- For the open source installation, the `
β’ Typically serve as the start agent (Hub Agent)| +| **Task Agents** (`internal`) | Specialized agents that perform specific tasks without direct user interaction. | β’ Focused on specific functions
β’ Return results to parent agents| +| **Pipeline Agents** (`pipeline`) | Sequential workflow execution agents that process data in a chain. | β’ Execute in sequence within a pipeline
β’ Cannot transfer to other agents directly| + + +--- + +## Agent Configuration + +Agents are configured through two main tabs in the Rowboat Studio interface: + +### **Instructions Tab** + + +#### Description +A clear description of the agent's role and responsibilities + +#### Instructions +Instructions are the backbone of the agent's behavior. Use the Copilot's structured format for consistency: + +**Recommended Structure:** +``` +## π§βπΌ Role: +[Clear description of the agent's role] + +## βοΈ Steps to Follow: +1. [Step 1] +2. [Step 2] +3. [Step 3] + +## π― Scope: +β In Scope: +- [What the agent should handle] + +β Out of Scope: +- [What the agent should NOT handle] + +## π Guidelines: +βοΈ Dos: +- [Positive behaviors] + +π« Don'ts: +- [Negative behaviors] +``` + +#### Examples +These help agents behave correctly in specific situations. Each example can include: +- A sample user message +- The expected agent response +- Any tool calls (if applicable) + +### **Configurations Tab** + +#### Name +Name of the agent + + +#### Behaviour +- **Agent Type**: Choose from `conversation`, `internal`, or `pipeline` +- **Model**: Select the LLM model (GPT-4.1, GPT-4o, google/gemini-2.5-flash, etc.) + +#### RAG +- **Add Source**: Connect data sources to enable RAG capabilities for the agent + +--- + +## Creating Your Initial Set of Agents + +Let Copilot bootstrap your agent graph. + +### Instruct Copilot + +Start by telling Copilot what your assistant is meant to do β it'll generate an initial set of agents with best-practice instructions, role definitions, and connected agents. + + +
+
+
+### Inspect the Output
+
+After applying the suggested agents, take a close look at each one's:
+- **Instructions**: Define how the agent behaves
+- **Examples**: Guide agent responses and tool use
+
+
+ 
+
+
+---
+
+## Updating Agent Behavior
+
+There are three ways to update an agent:
+
+### 1. With Copilot
+
+Copilot understands the current chat context and can help rewrite or improve an agent's behavior based on how it performed.
+
+
+ 
+
+
+
+
+### 2. Manual Edits
+
+You can always manually edit the agent's instructions.
+
+
+ 
+
+
+---
+
+
diff --git a/apps/docs/docs/using-rowboat/conversations.mdx b/apps/docs/docs/using-rowboat/conversations.mdx
new file mode 100644
index 000000000..c755f47d2
--- /dev/null
+++ b/apps/docs/docs/using-rowboat/conversations.mdx
@@ -0,0 +1,52 @@
+---
+title: "Conversations"
+description: "View and manage all conversations with your Rowboat agents"
+icon: "list-check"
+---
+
+## Overview
+
+The Conversations page in Rowboat shows you all the interactions between users and your agents. Here you can monitor conversations, view detailed message exchanges, and understand how your agents are performing.
+
+
+ 
+
+
+## What You'll See
+
+The Conversations page displays a list of all conversations organized by time:
+
+- **Today**: Recent conversations from today
+- **This week**: Conversations from the current week
+- **This month**: Conversations from the current month
+- **Older**: Conversations from previous months
+
+Each conversation shows:
+- **Conversation ID**: Unique identifier for the conversation
+- **Created time**: When the conversation started
+- **Reason**: What triggered the conversation (chat or job)
+
+## Viewing Conversation Details
+Click on any conversation to see the detailed view with all the message exchanges:
+
+
+ 
+
+
+**Conversation Metadata**: Shows the Conversation ID, creation time, and last update time.
+
+**Workflow**: Shows the workflow JSON
+
+**Turns**: Each conversation is made up of turns, where:
+- **Turn #1, #2, etc.**: Numbered sequence of interactions
+- **Reason badge**: Shows why each turn happened (chat, API, job, etc.)
+- **Timestamp**: When each turn occurred
+- **Input messages**: What was sent to your agents
+- **Output messages**: What your agents responded with
+
+### Turn Details
+
+Each turn displays:
+- **Input**: The messages sent to your agents (user messages, system messages)
+- **Output**: The responses from your agents
+- **Error information**: Any issues that occurred during processing
diff --git a/apps/docs/docs/using-rowboat/customise/custom-llms.mdx b/apps/docs/docs/using-rowboat/customise/custom-llms.mdx
new file mode 100644
index 000000000..64b27ca15
--- /dev/null
+++ b/apps/docs/docs/using-rowboat/customise/custom-llms.mdx
@@ -0,0 +1,53 @@
+---
+title: "Custom LLMs"
+description: "How to use and configure custom LLMs in Rowboat."
+
+---
+
+gpt-4.1 as the default model for agents and copilot. You can override these:
+
+ ```bash
+ export PROVIDER_DEFAULT_MODEL=claude-3-7-sonnet-latest
+ export PROVIDER_COPILOT_MODEL=gpt-4.1
+ ```
+
+ **Notes:**
+ - Copilot is optimized for gpt-4o/gpt-4.1. We strongly recommend using these models for best results.
+ - You can use different models for the copilot and each agent, but all must be from the same provider (e.g., LiteLLM).
+ - Rowboat is provider-agnostic β any backend implementing the OpenAI messages format should work.
+ - OpenAI-specific tools (like web_search) will not function with non-OpenAI providers. Remove such tools to avoid errors.
+ 
+
+
+## What You'll See
+
+The Jobs page displays a list of all job runs from your triggers, including:
+
+- **External trigger executions** from webhook events
+- **One-time trigger runs** from scheduled jobs
+- **Recurring trigger executions** from cron-based schedules
+
+Each job run displays the following key information:
+- **Job ID**: Unique identifier for the job run
+- **Status**: Indicates if the job succeeded, failed, or is in progress
+- **Reason**: The trigger or cause for the job (e.g., external trigger, scheduled, cron)
+- **Created Time**: When the job was executed
+
+## Viewing Job Details
+
+### Expand a Job Run
+
+Click on any job run to expand it and see detailed information about what happened during execution:
+
+
+ 
+
+
+**Basic job details**: Job ID, Status, creation time, Updated time, Conversation ID and Turn ID. By clicking on the Conversation ID, you can view more in-depth details about the run.
+
+**Job Reason**: Why the job triggered - either external trigger, scheduled, or cron.
+
+**Job Input**: The input data sent to your assistant.
+
+**Job Output**: The final output produced by your agents.
\ No newline at end of file
diff --git a/apps/docs/docs/using-rowboat/rag.mdx b/apps/docs/docs/using-rowboat/rag.mdx
new file mode 100644
index 000000000..772d034d5
--- /dev/null
+++ b/apps/docs/docs/using-rowboat/rag.mdx
@@ -0,0 +1,68 @@
+---
+title: "RAG (Data)"
+description: "How to use our inbuilt RAG"
+icon: "database"
+---
+
+# Using RAG in Rowboat
+
+Rowboat provides multiple ways to enhance your agents' context with Retrieval-Augmented Generation (RAG). This guide will help you set up and use each RAG feature.
+
+
+
+
+
+## RAG Features
+
+### 1. Text RAG
+
+Process and reason over text content directly
+
+
+### 2. File Uploads
+
+- Upload PDF files directly from your device
+- **Open Source Version**: Files are stored locally on your machine
+- **Managed Version**: Files are stored in cloud S3 storage
+- Files are parsed using OpenAI by default
+
+Each agent handles a specific part of the conversation and performs tasks using tools and instructions. | β’ Define behavior in plain language
β’ Connect agents into a graph
β’ Attach tools and RAG sources | +| **Playground** | Interactive testbed for conversations.
Lets you simulate end-user chats with your assistant and inspect agent behavior in real time. | β’ Real-time feedback and debugging
β’ See tool calls and agent handoffs
β’ Test individual agents or the whole system | +| **Copilot** | Your AI assistant for building assistants.
Copilot creates and updates agents, tools, and instructions based on your plain-English prompts. | β’ Understands full system context
β’ Improves agents based on playground chat
β’ Builds workflows intelligently and fast | + +> **Agents are the heart of every assistant.** Learn more about how they work in the Agents page. + +
+
+
+## Tool Types
+
+| Tool Type | Description | Use Case | Availability |
+|-----------|-------------|----------|--------------|
+| **Library Tools** | Pre-built integrations with popular services | Quick setup, no configuration needed | Managed and open source |
+| **MCP Tools** | Custom tools from MCP servers | Custom functionality, specialized APIs | Managed and open source |
+| **Webhook Tools** | HTTP endpoints for custom integrations | Your own systems, custom workflows | Open source only |
+
+
+## Library (Composio Tools)
+
+- Browse a library of 500+ toolkits from popular services
+- With 3000+ tools to choose from!
+- Click on a service to see available tools and add them to your workflow
+- Users must create a [Composio](https://composio.dev/) account and add their API key
+- Tools require authorization to work properly
+
+### Setting up Composio API Key
+
+To use Composio tools, get a Composio key and export it as an environment variable:
+
+```bash
+export COMPOSIO_API_KEY=your_api_key_here
+```
+
+
+
+
+### Creating External Triggers
+
+1. **Click New External Trigger**: Start the trigger creation process
+2. **Select a Toolkit**: Browse available toolkits or search for specific services
+3. **Choose Trigger Type**: Select the specific trigger from available options, click configure
+4. **Authenticate**: Complete OAuth2 flow or enter API keys for the selected service (your preferred method)
+5. **Configure**: Set up event filters and data mapping if required
+6. **Deploy**: Activate the trigger to start listening for events
+
+### Local Setup
+
+If you're running the open source version of Rowboat, you'll need to set up external triggers manually. In the managed version, this is all handled automatically for you.
+
+
+
+
+### Creating One-Time Triggers
+1. Set the exact execution time (date and time)
+2. Configure the input messages for your agents
+3. Deploy to schedule the execution
+
+---
+
+## Recurring Triggers (Cron-based Jobs)
+
+Recurring triggers execute your agents on a repeating schedule using cron expressions. They're ideal for daily reports, periodic maintenance, regular data syncs, and continuous monitoring tasks.
+
+
+ 
+
+
+### Creating Recurring Triggers
+1. Define the cron expression (e.g., `0 9 * * *` for daily at 9 AM)
+2. Configure the recurring message structure
+3. Enable the trigger to start the recurring schedule
+
+### Common Cron Patterns
+```cron
+0 9 * * * # Daily at 9:00 AM
+0 8 * * 1 # Every Monday at 8:00 AM
+*/15 * * * * # Every 15 minutes
+0 0 1 * * # First day of month at midnight
+```
+
diff --git a/apps/docs/docs/using_rag.md b/apps/docs/docs/using_rag.md
deleted file mode 100644
index 52deefadf..000000000
--- a/apps/docs/docs/using_rag.md
+++ /dev/null
@@ -1,103 +0,0 @@
-# Using RAG in Rowboat
-
-Rowboat provides multiple ways to enhance your agents' context with Retrieval-Augmented Generation (RAG). This guide will help you set up and use each RAG features.
-
-## Quick Start
-
-Text RAG and local file uploads are enabled by default - no configuration needed! Just start using them right away.
-
-## RAG Features
-
-### 1. Text RAG
-β
Enabled by default:
-
-- Process and reason over text content directly
-- No configuration required
-
-### 2. Local File Uploads
-β
Enabled by default:
-
-- Upload PDF files directly from your device
-- Files are stored locally
-- No configuration required
-- Files are parsed using OpenAI by default
-- For larger files, we recommend using Gemini models - see section below.
-
-#### 2.1 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
-```
-
-### 3. URL Scraping
-Rowboat uses Firecrawl for URL scraping. To enable URL scraping, set the following variables:
-
-```bash
-export USE_RAG_SCRAPING=true
-export FIRECRAWL_API_KEY=your_firecrawl_api_key
-```
-
-## Advanced RAG features
-
-### 1. File Uploads Backed by S3
-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
-```
-
-### 2. Changing Default Parsing Model
-
-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
-```
-
-### 3. 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
-export EMBEDDING_VECTOR_SIZE=1536
-```
-
-**Important NOTE**
-
-The default size for the vectors index is 1536. If you change this value, then you must delete the index and set it up again:
-```bash
-docker-compose --profile delete_qdrant --profile qdrant up --build delete_qdrant qdrant
-```
-followed by:
-```bash
-./start # this will recreate the index
-```
-
-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.
diff --git a/apps/docs/docs/using_the_sdk.md b/apps/docs/docs/using_the_sdk.md
deleted file mode 100644
index c867bcbc9..000000000
--- a/apps/docs/docs/using_the_sdk.md
+++ /dev/null
@@ -1,99 +0,0 @@
-# Using the Python SDK
-
-This is a guide on using the RowBoat Python SDK as an alternative to the [RowBoat HTTP API](/using_the_api) to power conversations with the assistant created in Studio.
-
-## Prerequisites
-- ``` pip install rowboat ```
-- [Deploy your assistant to production](/using_the_api/#deploy-your-assistant-to-production-on-studio)
-- [Obtain your `