AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
docs(blocks): Add AI/ML API integration guide and update LLM headers (#10402)
Dmitry0dd30e275c64
diff --git a/autogpt_platform/backend/backend/blocks/llm.py b/autogpt_platform/backend/backend/blocks/llm.pyindex 4b0e7f3d08..50f5b4f092 100644--- a/autogpt_platform/backend/backend/blocks/llm.py+++ b/autogpt_platform/backend/backend/blocks/llm.py@@ -676,7 +676,11 @@ async def llm_call(client = openai.OpenAI(base_url="https://api.aimlapi.com/v2",api_key=credentials.api_key.get_secret_value(),- default_headers={"X-Project": "AutoGPT"},+ default_headers={+ "X-Project": "AutoGPT",+ "X-Title": "AutoGPT",+ "HTTP-Referer": "https://github.com/Significant-Gravitas/AutoGPT",+ },)completion = client.chat.completions.create(diff --git a/docs/content/imgs/aimlapi/Step 1 AutoGPT Running.png b/docs/content/imgs/aimlapi/Step 1 AutoGPT Running.pngnew file mode 100644index 0000000000..66600f6105Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 1 AutoGPT Running.png differdiff --git a/docs/content/imgs/aimlapi/Step 2 Build Screen.png b/docs/content/imgs/aimlapi/Step 2 Build Screen.pngnew file mode 100644index 0000000000..45d6c6700fBinary files /dev/null and b/docs/content/imgs/aimlapi/Step 2 Build Screen.png differdiff --git a/docs/content/imgs/aimlapi/Step 3 AI Block.png b/docs/content/imgs/aimlapi/Step 3 AI Block.pngnew file mode 100644index 0000000000..b8123cfc66Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 3 AI Block.png differdiff --git a/docs/content/imgs/aimlapi/Step 4 AI Generator Block.png b/docs/content/imgs/aimlapi/Step 4 AI Generator Block.pngnew file mode 100644index 0000000000..92a882351aBinary files /dev/null and b/docs/content/imgs/aimlapi/Step 4 AI Generator Block.png differdiff --git a/docs/content/imgs/aimlapi/Step 5 AIMLAPI Models.png b/docs/content/imgs/aimlapi/Step 5 AIMLAPI Models.pngnew file mode 100644index 0000000000..3f7727da6dBinary files /dev/null and b/docs/content/imgs/aimlapi/Step 5 AIMLAPI Models.png differdiff --git a/docs/content/imgs/aimlapi/Step 6.1 Key Placeholder.png b/docs/content/imgs/aimlapi/Step 6.1 Key Placeholder.pngnew file mode 100644index 0000000000..43ea616f51Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 6.1 Key Placeholder.png differdiff --git a/docs/content/imgs/aimlapi/Step 6.2 No Fill Key Placeholder.png b/docs/content/imgs/aimlapi/Step 6.2 No Fill Key Placeholder.pngnew file mode 100644index 0000000000..95363da76cBinary files /dev/null and b/docs/content/imgs/aimlapi/Step 6.2 No Fill Key Placeholder.png differdiff --git a/docs/content/imgs/aimlapi/Step 6.3 Filled Key Placeholder.png b/docs/content/imgs/aimlapi/Step 6.3 Filled Key Placeholder.pngnew file mode 100644index 0000000000..072a61727aBinary files /dev/null and b/docs/content/imgs/aimlapi/Step 6.3 Filled Key Placeholder.png differdiff --git a/docs/content/imgs/aimlapi/Step 6.4 Overview.png b/docs/content/imgs/aimlapi/Step 6.4 Overview.pngnew file mode 100644index 0000000000..f4b605ae89Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 6.4 Overview.png differdiff --git a/docs/content/imgs/aimlapi/Step 7.1 Save.png b/docs/content/imgs/aimlapi/Step 7.1 Save.pngnew file mode 100644index 0000000000..275e812567Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 7.1 Save.png differdiff --git a/docs/content/imgs/aimlapi/Step 8 Run.png b/docs/content/imgs/aimlapi/Step 8 Run.pngnew file mode 100644index 0000000000..c4d7849331Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 8 Run.png differdiff --git a/docs/content/imgs/aimlapi/Step 9 Output.png b/docs/content/imgs/aimlapi/Step 9 Output.pngnew file mode 100644index 0000000000..7176c5edc0Binary files /dev/null and b/docs/content/imgs/aimlapi/Step 9 Output.png differdiff --git a/docs/content/index.md b/docs/content/index.mdindex cd69844364..d22bb2885e 100644--- a/docs/content/index.md+++ b/docs/content/index.md@@ -64,11 +64,12 @@ You can learn more under: [Build your own Blocks](platform/new_blocks.md)The platform comes pre-integrated with cutting-edge LLM providers:-- OpenAI-- Anthropic-- AI/ML API-- Groq-- Llama+- OpenAI - https://openai.com/+- Anthropic - https://www.anthropic.com/+- Groq - https://groq.com/+- Llama - https://llamaindex.ai/+- AI/ML API - [https://aimlapi.com/](https://aimlapi.com/?utm_source=autogpt&utm_medium=github&utm_campaign=integration)+ - AI/ML API provides 300+ AI models including Deepseek, Gemini, ChatGPT. The models run at enterprise-grade rate limits and uptimes.## License Overviewdiff --git a/docs/content/platform/aimlapi.md b/docs/content/platform/aimlapi.mdnew file mode 100644index 0000000000..785fc50e3a--- /dev/null+++ b/docs/content/platform/aimlapi.md@@ -0,0 +1,139 @@++# 🧠 Running AI/ML API with AutoGPT++Follow these steps to connect **AI/ML API** with the **AutoGPT** platform for high-performance AI text generation.++---++## ✅ Prerequisites++1. Make sure you have gone through and completed the [AutoGPT Setup Guide](https://docs.agpt.co/platform/getting-started/), and AutoGPT is running locally at `http://localhost:3000`.+2. You have an **API key** from [AI/ML API](https://aimlapi.com/app/keys?utm_source=autogpt&utm_medium=github&utm_campaign=integration).++---++## ⚙️ Setup Steps++### 1. Start AutoGPT Locally++Follow the official guide:+[📖 AutoGPT Getting Started Guide](https://docs.agpt.co/platform/getting-started/)++Make sure AutoGPT is running and accessible at:+[http://localhost:3000](http://localhost:3000)++> 💡 Keep AutoGPT running in a terminal or Docker throughout the session.++++---++### 2. Open the Visual Builder++Open your browser and go to:+[http://localhost:3000/build](http://localhost:3000/build)++Or click **“Build”** in the navigation bar.++++---++### 3. Add an AI Text Generator Block++1. Click the **"Blocks"** button on the left sidebar.++++2. In the search bar, type `AI Text Generator`.+3. Drag the block into the canvas.++++---++### 4. Select an AI/ML API Model++Click the AI Text Generator block to configure it.++In the **LLM Model** dropdown, select one of the supported models from AI/ML API:++++| Model ID | Speed | Reasoning Quality | Best For |+| ---------------------------------------------- | ------ | ----------------- | ------------------------ |+| `Qwen/Qwen2.5-72B-Instruct-Turbo` | Medium | High | Text-based tasks |+| `nvidia/llama-3.1-nemotron-70b-instruct` | Medium | High | Analytics and reasoning |+| `meta-llama/Llama-3.3-70B-Instruct-Turbo` | Low | Very High | Complex multi-step tasks |+| `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` | Low | Very High | Deep reasoning |+| `meta-llama/Llama-3.2-3B-Instruct-Turbo` | High | Medium | Fast responses |++> ✅ These models are available via OpenAI-compatible API from [AI/ML API](https://aimlapi.com/app/?utm_source=autogpt&utm_medium=github&utm_campaign=integration)++---++### 5. Configure the Prompt and API Key++Inside the **AI Text Generator** block:++1. Enter your prompt text in the **Prompt** field.+2. Enter your **AI/ML API Key** in the designated field.++🔐 You can get your key from:+[https://aimlapi.com/app/keys/](https://aimlapi.com/app/keys?utm_source=autogpt&utm_medium=github&utm_campaign=integration)++++++++++---++### 6. Save Your Agent++Click the **“Save”** button at the top-right of the builder interface:++1. Give your agent a name (e.g., `aimlapi_test_agent`).+2. Click **“Save Agent”** to confirm.++++> 💡 Saving allows reuse, scheduling, and chaining in larger workflows.++---++### 7. Run Your Agent++From the workspace:++1. Press **“Run”** next to your saved agent.+2. The request will be sent to the selected AI/ML API model.++++---++### 8. View the Output++1. Scroll to the **AI Text Generator** block.+2. Check the **Output** panel below it.+3. You can copy, export, or pass the result to further blocks.++++---++## 🔄 Expand Your Agent++Now that AI/ML API is connected, expand your workflow by chaining additional blocks:++* 🔧 **Tools** – fetch URLs, call APIs, scrape data+* 🧠 **Memory** – retain context across interactions+* ⚙️ **Actions / Chains** – create full pipelines++---++🎉 You’re now generating AI responses using enterprise-grade models from **AI/ML API** in **AutoGPT**!diff --git a/docs/mkdocs.yml b/docs/mkdocs.ymlindex 1d7b17e811..126dfbc154 100644--- a/docs/mkdocs.yml+++ b/docs/mkdocs.yml@@ -19,6 +19,7 @@ nav:- Agent Blocks: platform/agent-blocks.md- Build your own Blocks: platform/new_blocks.md- Using Ollama: platform/ollama.md+ - Using AI/ML API: platform/aimlapi.md- Using D-ID: platform/d_id.md- Blocks: platform/blocks/blocks.md- Contributing: