diff --git a/docs/content/Deploying/DocsGPT-Settings.mdx b/docs/content/Deploying/DocsGPT-Settings.mdx index fd548be6..42c7963a 100644 --- a/docs/content/Deploying/DocsGPT-Settings.mdx +++ b/docs/content/Deploying/DocsGPT-Settings.mdx @@ -214,6 +214,31 @@ If you have configured `AUTH_TYPE=simple_jwt`, the DocsGPT frontend will prompt }} /> +## S3 Storage Backend + +By default DocsGPT stores files locally. Set `STORAGE_TYPE=s3` to use Amazon S3 instead. + +| Setting | Description | Default | +| --- | --- | --- | +| `STORAGE_TYPE` | `local` or `s3` | `local` | +| `S3_BUCKET_NAME` | S3 bucket name | `docsgpt-test-bucket` | +| `SAGEMAKER_ACCESS_KEY` | AWS access key ID | — | +| `SAGEMAKER_SECRET_KEY` | AWS secret access key | — | +| `SAGEMAKER_REGION` | AWS region | — | +| `URL_STRATEGY` | `backend` (proxy through API) or `s3` (direct S3 URLs) | `backend` | + +The S3 credentials use `SAGEMAKER_*` variable names because they are shared with the SageMaker integration. + +```env +STORAGE_TYPE=s3 +S3_BUCKET_NAME=your-bucket-name +SAGEMAKER_ACCESS_KEY=your-aws-access-key-id +SAGEMAKER_SECRET_KEY=your-aws-secret-access-key +SAGEMAKER_REGION=us-east-1 +``` + +Your IAM user needs these permissions on the bucket: `s3:PutObject`, `s3:GetObject`, `s3:DeleteObject`, `s3:ListBucket`, `s3:HeadObject`. + ## Exploring More Settings These are just the basic settings to get you started. The `settings.py` file contains many more advanced options that you can explore to further customize DocsGPT, such as: diff --git a/docs/content/Guides/How-to-use-different-LLM.mdx b/docs/content/Guides/How-to-use-different-LLM.mdx index 217bc690..f92b3ce1 100644 --- a/docs/content/Guides/How-to-use-different-LLM.mdx +++ b/docs/content/Guides/How-to-use-different-LLM.mdx @@ -35,8 +35,34 @@ Choose the LLM of your choice. For open source version please edit `LLM_PROVIDER`, `LLM_NAME` and others in the .env file. Refer to [⚙️ App Configuration](/Deploying/DocsGPT-Settings) for more information. ### Step 2 Visit [☁️ Cloud Providers](/Models/cloud-providers) for the updated list of online models. Make sure you have the right API_KEY and correct LLM_PROVIDER. -For self-hosted please visit [🖥️ Local Inference](/Models/local-inference). +For self-hosted please visit [🖥️ Local Inference](/Models/local-inference). +## Fallback LLM + +DocsGPT can automatically switch to a fallback LLM when the primary model fails, including mid-stream. This works with both streaming and non-streaming requests. + +**Fallback order:** +1. Per-agent backup models (other models configured on the same agent) +2. Global fallback (`FALLBACK_LLM_*` env vars below) +3. Error returned if all fail + +| Setting | Description | Default | +| --- | --- | --- | +| `FALLBACK_LLM_PROVIDER` | Provider name (e.g., `openai`, `anthropic`, `google`) | — | +| `FALLBACK_LLM_NAME` | Model name (e.g., `gpt-4o`, `claude-sonnet-4-20250514`) | — | +| `FALLBACK_LLM_API_KEY` | API key for the fallback provider | Falls back to `API_KEY` | + +All three (`FALLBACK_LLM_PROVIDER`, `FALLBACK_LLM_NAME`, and an API key) must resolve for the global fallback to activate. + +```env +FALLBACK_LLM_PROVIDER=anthropic +FALLBACK_LLM_NAME=claude-sonnet-4-20250514 +FALLBACK_LLM_API_KEY=sk-ant-your-anthropic-key +``` + + +For maximum resilience, use a fallback provider from a different cloud than your primary. Each agent can also have multiple models configured — the other models are tried first before the global fallback. + diff --git a/docs/content/Guides/Integrations/_meta.js b/docs/content/Guides/Integrations/_meta.js index 8eb263d6..6630e25b 100644 --- a/docs/content/Guides/Integrations/_meta.js +++ b/docs/content/Guides/Integrations/_meta.js @@ -2,5 +2,13 @@ export default { "google-drive-connector": { "title": "🔗 Google Drive", "href": "/Guides/Integrations/google-drive-connector" + }, + "sharepoint-connector": { + "title": "🔗 SharePoint / OneDrive", + "href": "/Guides/Integrations/sharepoint-connector" + }, + "mcp-tool-integration": { + "title": "🔗 MCP Tools", + "href": "/Guides/Integrations/mcp-tool-integration" } } diff --git a/docs/content/Guides/Integrations/mcp-tool-integration.mdx b/docs/content/Guides/Integrations/mcp-tool-integration.mdx new file mode 100644 index 00000000..d33e1b94 --- /dev/null +++ b/docs/content/Guides/Integrations/mcp-tool-integration.mdx @@ -0,0 +1,66 @@ +--- +title: MCP Tool Integration +description: Connect external tools to DocsGPT agents using the Model Context Protocol (MCP) standard. +--- + +import { Callout } from 'nextra/components' +import { Steps } from 'nextra/components' + +# MCP Tool Integration + +The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) integration lets you connect external tool servers to DocsGPT. Your agents can then discover and call tools provided by those servers during conversations — for example, querying a CRM, running code, or accessing a database. + +## Setup + + + +### Step 1: Configure Environment Variables (Optional) + +Only needed if your MCP servers use OAuth authentication: + +```env +MCP_OAUTH_REDIRECT_URI=https://yourdomain.com/api/mcp_server/callback +``` + +If not set, falls back to `API_URL/api/mcp_server/callback`. + +### Step 2: Add an MCP Server + +Go to **Settings** > **Tools** > **Add Tool** > **MCP Server**. Enter the server URL, select an auth type, and click **Test Connection** to verify, then **Save**. + +### Step 3: Enable for Your Agent + +In your agent configuration, enable the MCP tools you want the agent to use. + + + +## Authentication Types + +| Auth Type | Config Fields | +|-----------|---------------| +| **None** | — | +| **Bearer** | `bearer_token` | +| **API Key** | `api_key`, `api_key_header` (default: `X-API-Key`) | +| **Basic** | `username`, `password` | +| **OAuth** | `oauth_scopes` (optional) | + + +For OAuth in production, `MCP_OAUTH_REDIRECT_URI` must be a publicly accessible URL pointing to your DocsGPT backend. + + +## API Endpoints + +| Endpoint | Method | Description | +|----------|--------|-------------| +| `/api/mcp_server/test` | POST | Test a connection without saving | +| `/api/mcp_server/save` | POST | Save or update a server configuration | +| `/api/mcp_server/callback` | GET | OAuth callback handler | +| `/api/mcp_server/oauth_status/` | GET | Poll OAuth flow status | +| `/api/mcp_server/auth_status` | GET | Batch check auth status for all MCP tools | + +## Troubleshooting + +- **Connection refused** — Verify the URL and that the server is reachable from your backend. +- **403 Forbidden** — Check credentials and permissions. +- **Timed out** — Default is 30s; increase timeout in tool config (max 300s). +- **OAuth "needs_auth" persists** — Verify `MCP_OAUTH_REDIRECT_URI` is correct and Redis is running. diff --git a/docs/content/Guides/Integrations/sharepoint-connector.mdx b/docs/content/Guides/Integrations/sharepoint-connector.mdx new file mode 100644 index 00000000..cf8b27bf --- /dev/null +++ b/docs/content/Guides/Integrations/sharepoint-connector.mdx @@ -0,0 +1,63 @@ +--- +title: SharePoint / OneDrive Connector +description: Connect your Microsoft SharePoint or OneDrive as an external knowledge base to upload and process files directly. +--- + +import { Callout } from 'nextra/components' +import { Steps } from 'nextra/components' + +# SharePoint / OneDrive Connector + +Connect your SharePoint or OneDrive account to upload and process files directly as an external knowledge base. Supports Office files, PDFs, text files, CSVs, images, and more. Authentication is handled via Microsoft Entra ID (Azure AD) with automatic token refresh. + +## Setup + + + +### Step 1: Create an App Registration in Azure + +1. Go to the [Azure Portal](https://portal.azure.com/) > **Microsoft Entra ID** > **App registrations** > **New registration** +2. Set **Redirect URI** (Web) to: + - Local: `http://localhost:7091/api/connectors/callback?provider=share_point` + - Production: `https://yourdomain.com/api/connectors/callback?provider=share_point` + +### Step 2: Configure API Permissions + +In your App Registration, go to **API permissions** > **Add a permission** > **Microsoft Graph** > **Delegated permissions** and add: `Files.Read`, `Files.Read.All`, `Sites.Read.All`. Grant admin consent if possible. + +### Step 3: Create a Client Secret + +Go to **Certificates & secrets** > **New client secret**. Copy the secret value immediately (it won't be shown again). + +### Step 4: Configure Environment Variables + +Add to your `.env` file: + +```env +MICROSOFT_CLIENT_ID=your-azure-ad-client-id +MICROSOFT_CLIENT_SECRET=your-azure-ad-client-secret +MICROSOFT_TENANT_ID=your-azure-ad-tenant-id +``` + +| Variable | Description | Required | Default | +|----------|-------------|----------|---------| +| `MICROSOFT_CLIENT_ID` | Application (client) ID from App Registration overview | Yes | — | +| `MICROSOFT_CLIENT_SECRET` | Client secret value | Yes | — | +| `MICROSOFT_TENANT_ID` | Directory (tenant) ID | No | `common` | +| `MICROSOFT_AUTHORITY` | Login endpoint override | No | Auto-constructed | + + +`MICROSOFT_TENANT_ID=common` (the default) allows any Microsoft account to authenticate. Set this to your specific tenant ID in production. + + +### Step 5: Restart and Use + +Restart your application, then go to the upload section in DocsGPT and select **SharePoint / OneDrive** as the source. You'll be redirected to Microsoft to sign in, then can browse and select files to process. + + + +## Troubleshooting + +- **Option not appearing** — Verify `MICROSOFT_CLIENT_ID` and `MICROSOFT_CLIENT_SECRET` are set, then restart. +- **Authentication failed** — Check that the redirect URI matches exactly, including `?provider=share_point`. +- **Permission denied** — Ensure admin consent is granted and the user has access to the target files. diff --git a/docs/content/Guides/_meta.js b/docs/content/Guides/_meta.js index a5c91e04..25c49b20 100644 --- a/docs/content/Guides/_meta.js +++ b/docs/content/Guides/_meta.js @@ -29,7 +29,7 @@ export default { "title": "OCR", "href": "/Guides/ocr" }, - "Integrations": { +"Integrations": { "title": "🔗 Integrations" } }