diff --git a/docs/content/Deploying/Amazon-Lightsail.mdx b/docs/content/Deploying/Amazon-Lightsail.mdx index 24aef74b..a83e6959 100644 --- a/docs/content/Deploying/Amazon-Lightsail.mdx +++ b/docs/content/Deploying/Amazon-Lightsail.mdx @@ -70,9 +70,9 @@ Inside the DocsGPT folder create a `.env` file and copy the contents of `.env_sa Make sure your `.env` file looks like this: ``` -OPENAI_API_KEY=(Your OpenAI API key) +API_KEY= +LLM_NAME=docsgpt VITE_API_STREAMING=true -SELF_HOSTED_MODEL=false ``` To save the file, press CTRL+X, then Y, and then ENTER. diff --git a/docs/content/Deploying/DocsGPT-Settings.mdx b/docs/content/Deploying/DocsGPT-Settings.mdx index b51f3d6d..fd548be6 100644 --- a/docs/content/Deploying/DocsGPT-Settings.mdx +++ b/docs/content/Deploying/DocsGPT-Settings.mdx @@ -104,7 +104,7 @@ DocsGPT can transcribe audio in two places: - Voice input in the chat. - Audio file ingestion. Uploaded `.wav`, `.mp3`, `.m4a`, `.ogg`, and `.webm` files are transcribed first and then passed through the normal parser, chunking, embedding, and indexing pipeline. -For an end-to-end walkthrough, see the [Speech and Audio Guide](/Guides/speech-and-audio). +The settings below control speech-to-text behaviour for both voice input and audio file ingestion. | Setting | Purpose | Typical values | | --- | --- | --- | diff --git a/docs/content/Deploying/Railway.mdx b/docs/content/Deploying/Railway.mdx index 89928ab2..d6e74a24 100644 --- a/docs/content/Deploying/Railway.mdx +++ b/docs/content/Deploying/Railway.mdx @@ -86,13 +86,9 @@ Make sure your `.env` file looks like this: ``` - -OPENAI_API_KEY=(Your OpenAI API key) - +API_KEY= +LLM_NAME=docsgpt VITE_API_STREAMING=true - -SELF_HOSTED_MODEL=false - ``` diff --git a/docs/content/Extensions/api-key-guide.mdx b/docs/content/Extensions/api-key-guide.mdx index f1b83633..41520395 100644 --- a/docs/content/Extensions/api-key-guide.mdx +++ b/docs/content/Extensions/api-key-guide.mdx @@ -11,18 +11,18 @@ DocsGPT API keys are essential for developers and users who wish to integrate th After uploading your document, you can obtain an API key either through the graphical user interface or via an API call: -- **Graphical User Interface:** Navigate to the Settings section of the DocsGPT web app, find the API Keys option, and press 'Create New' to generate your key. -- **API Call:** Alternatively, you can use the `/api/create_api_key` endpoint to create a new API key. For detailed instructions, visit [DocsGPT API Documentation](https://gptcloud.arc53.com/). +- **Graphical User Interface:** Navigate to the Settings section of the DocsGPT web app, find the Agents option, and press 'Create New' to generate a new agent (which includes an API key). +- **API Call:** Alternatively, you can use the `/api/create_agent` endpoint to create a new agent. An API key is automatically generated for each agent. For detailed instructions, visit [DocsGPT API Documentation](https://gptcloud.arc53.com/). ## Understanding Key Variables -Upon creating your API key, you will encounter several key variables. Each serves a specific purpose: +Upon creating your agent, you will encounter several key variables. Each serves a specific purpose: -- **Name:** Assign a name to your API key for easy identification. -- **Source:** Indicates the source document(s) linked to your API key, which DocsGPT will use to generate responses. -- **ID:** A unique identifier for your API key. You can view this by making a call to `/api/get_api_keys`. -- **Key:** The API key itself, which will be used in your application to authenticate API requests. +- **Name:** Assign a name to your agent for easy identification. +- **Source:** Indicates the source document(s) linked to your agent, which DocsGPT will use to generate responses. +- **ID:** A unique identifier for your agent. You can view this by making a call to `/api/get_agents`. +- **Key:** The API key for the agent, which will be used in your application to authenticate API requests. -With your API key ready, you can now integrate DocsGPT into your application, such as the DocsGPT Widget or any other software, via `/api/answer` or `/stream` endpoints. The source document is preset with the API key, allowing you to bypass fields like `selectDocs` and `active_docs` during implementation. +With your API key ready, you can now integrate DocsGPT into your application, such as the DocsGPT Widget or any other software, via `/api/answer` or `/stream` endpoints. The source document is preset with the agent, allowing you to bypass fields like `selectDocs` and `active_docs` during implementation. Congratulations on taking the first step towards enhancing your applications with DocsGPT! diff --git a/docs/content/Guides/Architecture.mdx b/docs/content/Guides/Architecture.mdx index 247abda6..d981dc63 100644 --- a/docs/content/Guides/Architecture.mdx +++ b/docs/content/Guides/Architecture.mdx @@ -64,7 +64,7 @@ flowchart LR * **Technology:** Supports multiple vector databases. * **Responsibility:** Vector Stores are used to store and retrieve vector embeddings of document chunks. This enables semantic search and retrieval of relevant document snippets in response to user queries. * **Key Features:** - * Supports vector databases including FAISS, Elasticsearch, Qdrant, Milvus, and LanceDB. + * Supports vector databases including FAISS, Elasticsearch, Qdrant, Milvus, MongoDB Atlas Vector Search, and pgvector. * Provides storage and indexing of high-dimensional vector embeddings. * Enables editing and updating of vector indexes including specific chunks. diff --git a/docs/content/Guides/How-to-train-on-other-documentation.mdx b/docs/content/Guides/How-to-train-on-other-documentation.mdx index 4e11d6fa..4b233c08 100644 --- a/docs/content/Guides/How-to-train-on-other-documentation.mdx +++ b/docs/content/Guides/How-to-train-on-other-documentation.mdx @@ -16,7 +16,7 @@ Training on other documentation sources can greatly enhance the versatility and Make sure you have the document on which you want to train on ready with you on the device which you are using .You can also use links to the documentation to train on. - Note: The document should be either of the given file formats .pdf, .txt, .rst, .docx, .md, .zip and limited to 25mb.You can also train using the link of the documentation. + Note: Supported file formats include .pdf, .txt, .rst, .docx, .md, .mdx, .csv, .epub, .html, .json, .xlsx, .pptx, .png, .jpg, .jpeg, and audio files (.wav, .mp3, .m4a, .ogg, .webm). You can also train using the link of the documentation. diff --git a/docs/content/Guides/My-AI-answers-questions-using-external-knowledge.mdx b/docs/content/Guides/My-AI-answers-questions-using-external-knowledge.mdx index 318bf41b..96d9ee6b 100644 --- a/docs/content/Guides/My-AI-answers-questions-using-external-knowledge.mdx +++ b/docs/content/Guides/My-AI-answers-questions-using-external-knowledge.mdx @@ -7,20 +7,10 @@ description: If your AI uses external knowledge and is not explicit enough, it is ok, because we try to make DocsGPT friendly. -But if you want to adjust it, here is a simple way:- - -- Got to `application/prompts/chat_combine_prompt.txt` - -- And change it to +But if you want to adjust it, prompts are now managed through the UI and API using a template-based system. See the [Customising Prompts](/Guides/Customising-prompts) guide for details. +To make the AI stricter about staying on-topic, edit your active prompt template (via **Sidebar → Settings → Active Prompt**) to include instructions like: ``` - -You are a DocsGPT, friendly and helpful AI assistant by Arc53 that provides help with documents. You give thorough answers with code examples, if possible. -Write an answer for the question below based on the provided context. If the context provides insufficient information, reply "I cannot answer". -You have access to chat history and can use it to help answer the question. ----------------- -{summaries} - ``` diff --git a/docs/content/quickstart.mdx b/docs/content/quickstart.mdx index 394276a8..60654a73 100644 --- a/docs/content/quickstart.mdx +++ b/docs/content/quickstart.mdx @@ -70,7 +70,7 @@ The easiest way to launch DocsGPT is using the provided `setup.sh` script. This To stop DocsGPT, simply open a new terminal in the `DocsGPT` directory and run: ```bash - docker compose -f deployment/docker-compose.yaml down + docker compose -f deployment/docker-compose-hub.yaml down ``` (or the specific `docker compose` command shown at the end of the `setup.sh` execution, which may include optional compose files depending on your choices).