mirror of
https://github.com/arc53/DocsGPT.git
synced 2025-11-29 08:33:20 +00:00
models+guide-upd+extentions
This commit is contained in:
@@ -1,3 +1,8 @@
|
||||
---
|
||||
title: Customizing Prompts
|
||||
description: This guide will explain how to change prompts in DocsGPT and why it might be benefitial. Additionaly this article expains additional variables that can be used in prompts.
|
||||
---
|
||||
|
||||
import Image from 'next/image'
|
||||
|
||||
# Customizing the Main Prompt
|
||||
@@ -34,6 +39,8 @@ When using code examples, use the following format:
|
||||
{summaries}
|
||||
```
|
||||
|
||||
Note that `{summaries}` allows model to see and respond to your upploaded documents. If you don't want this functionality you can safely remove it from the customized prompt.
|
||||
|
||||
Feel free to customize the prompt to align it with your specific use case or the kind of responses you want from the AI. For example, you can focus on specific document types, industries, or topics to get more targeted results.
|
||||
|
||||
## Conclusion
|
||||
|
||||
@@ -1,3 +1,7 @@
|
||||
---
|
||||
title: How to Train on Other Documentation
|
||||
description: A step-by-step guide on how to effectively train DocsGPT on additional documentation sources.
|
||||
---
|
||||
|
||||
import { Callout } from 'nextra/components'
|
||||
import Image from 'next/image'
|
||||
|
||||
@@ -1,3 +1,7 @@
|
||||
---
|
||||
title:
|
||||
description:
|
||||
---
|
||||
|
||||
import { Callout } from 'nextra/components'
|
||||
import Image from 'next/image'
|
||||
@@ -26,24 +30,13 @@ Choose the LLM of your choice.
|
||||
<Image src="/llms.gif" alt="prompts" width={800} height={500} />
|
||||
|
||||
### For Open source llm change:
|
||||
<Steps >
|
||||
<Steps>
|
||||
### Step 1
|
||||
For open source you have to edit .env file with LLM_NAME with their desired LLM name.
|
||||
For open source version please edit `LLM_NAME`, `MODEL_NAME` and others in the .env file. Refer to [⚙️ App Configuration](/Deploying/DocsGPT-Settings) for more information.
|
||||
### Step 2
|
||||
All the supported LLM providers are here application/llm and you can check what env variable are needed for each
|
||||
List of latest supported LLMs are https://github.com/arc53/DocsGPT/blob/main/application/llm/llm_creator.py
|
||||
### Step 3
|
||||
Visit application/llm and select the file of your selected llm and there you will find the specific requirements needed to be filled in order to use it,i.e API key of that llm.
|
||||
Visit [☁️ Cloud Providers](/Models/cloud-providers) for the updated list of online models. Make sure you have the right API_KEY and correct LLM_NAME.
|
||||
For self-hosted please visit [🖥️ Local Inference](/Models/local-inference).
|
||||
</Steps>
|
||||
|
||||
### For OpenAI-Compatible Endpoints:
|
||||
DocsGPT supports the use of OpenAI-compatible endpoints through base URL substitution. This feature allows you to use alternative AI models or services that implement the OpenAI API interface.
|
||||
|
||||
|
||||
Set the OPENAI_BASE_URL in your environment. You can change .env file with OPENAI_BASE_URL with the desired base URL or docker-compose.yml file and add the environment variable to the backend container.
|
||||
|
||||
> Make sure you have the right API_KEY and correct LLM_NAME.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,8 @@
|
||||
---
|
||||
title:
|
||||
description:
|
||||
---
|
||||
|
||||
# Avoiding hallucinations
|
||||
|
||||
If your AI uses external knowledge and is not explicit enough, it is ok, because we try to make DocsGPT friendly.
|
||||
@@ -9,10 +9,12 @@
|
||||
},
|
||||
"How-to-use-different-LLM": {
|
||||
"title": "️🤖 How to use different LLM's",
|
||||
"href": "/Guides/How-to-use-different-LLM"
|
||||
"href": "/Guides/How-to-use-different-LLM",
|
||||
"display": "hidden"
|
||||
},
|
||||
"My-AI-answers-questions-using-external-knowledge": {
|
||||
"title": "💭️ Avoiding hallucinations",
|
||||
"href": "/Guides/My-AI-answers-questions-using-external-knowledge"
|
||||
"href": "/Guides/My-AI-answers-questions-using-external-knowledge",
|
||||
"display": "hidden"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user