LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-12-02 10:03:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into New-prompt-

Browse Source
This commit is contained in:
Alex
2023-10-22 11:16:03 -04:00
committed by GitHub
parent d7b28a3586 e3e8e67cb4
commit 9303746d80
41 changed files with 983 additions and 426 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
docs/README.md
View File

@@ -1 +1,53 @@
# nextra-docsgpt
# nextra-docsgpt
## Setting Up Docs Folder of DocsGPT Locally
### 1. Clone the DocsGPT repository:
```
git clone https://github.com/arc53/DocsGPT.git
```
### 2. Navigate to the docs folder:
```
cd DocsGPT/docs
```
The docs folder contains the markdown files that make up the documentation. The majority of the files are in the pages directory. Some notable files in this folder include:
`index.mdx`: The main documentation file.
`_app.js`: This file is used to customize the default Next.js application shell.
`theme.config.jsx`: This file is for configuring the Nextra theme for the documentation.
### 3. Verify that you have Node.js and npm installed in your system. You can check by running:
```
node --version
npm --version
```
### 4. If not installed, download Node.js and npm from the respective official websites.
### 5. Once you have Node.js and npm running, proceed to install yarn - another package manager that helps to manage project dependencies:
```
npm install --global yarn
```
### 6. Install the project dependencies using yarn:
```
yarn install
```
### 7. After the successful installation of the project dependencies, start the local server:
```
yarn dev
```
- Now, you should be able to view the docs on your local environment by visiting `http://localhost:5000`. You can explore the different markdown files and make changes as you see fit.
- Footnotes: This guide assumes you have Node.js and npm installed. The guide involves running a local server using yarn, and viewing the documentation offline. If you encounter any issues, it may be worth verifying your Node.js and npm installations and whether you have installed yarn correctly.

8
docs/package.json
View File

@@ -1,4 +1,10 @@
{
"scripts":{
"dev": "next dev",
"build": "next build",
"start": "next start"
},
"license": "MIT",
"dependencies": {
"@vercel/analytics": "^1.0.2",
"docsgpt": "^0.2.4",
@@ -8,4 +14,4 @@
"react": "^18.2.0",
"react-dom": "^18.2.0"
}
}
}

62
docs/pages/Deploying/Hosting-the-app.md
View File

@@ -4,45 +4,38 @@ Here's a step-by-step guide on how to setup an Amazon Lightsail instance to host
## Configuring your instance
(If you know how to create a Lightsail instance, you can skip to the recommended configuration part by clicking here).
(If you know how to create a Lightsail instance, you can skip to the recommended configuration part by clicking [here](#connecting-to-your-newly-created-instance)).
### 1. Create an account or login to https://lightsail.aws.amazon.com
### 1. Create an AWS Account:
If you haven't already, create or log in to your AWS account at https://lightsail.aws.amazon.com.
### 2. Click on "Create instance"
### 2. Create an Instance:
### 3. Create your instance
a. Click "Create Instance."
The first step is to select the "Instance location". In most cases, there's no need to switch locations as the default one will work well.
b. Select the "Instance location." In most cases, the default location works fine.
After that, it is time to pick your Instance Image. We recommend using "Linux/Unix" as the image and "Ubuntu 20.04 LTS" as the Operating System.
c. Choose "Linux/Unix" as the image and "Ubuntu 20.04 LTS" as the Operating System.
As for instance plan, it'll vary depending on your unique demands, but a "1 GB, 1vCPU, 40GB SSD and 2TB transfer" setup should cover most scenarios.
d. Configure the instance plan based on your requirements. A "1 GB, 1vCPU, 40GB SSD, and 2TB transfer" setup is recommended for most scenarios.
Lastly, Identify your instance by giving it a unique name and then hit "Create instance".
e. Give your instance a unique name and click "Create Instance."
PS: Once you create your instance, it'll likely take a few minutes for the setup to be completed.
PS: It may take a few minutes for the instance setup to complete.
#### The recommended configuration is as follows:
### Connecting to Your newly created Instance
- Ubuntu 20.04 LTS
- 1GB RAM
- 1vCPU
- 40GB SSD Hard Drive
- 2TB transfer
Your instance will be ready a few minutes after creation. To access it, open the instance and click "Connect using SSH."
### Connecting to your newly created instance
#### Clone the DocsGPT Repository
Your instance will be ready for use a few minutes after being created. To access it, just open it up and click on "Connect using SSH".
#### Clone the repository
A terminal window will pop up, and the first step will be to clone the DocsGPT git repository:
A terminal window will pop up, and the first step will be to clone the DocsGPT Git repository:
`git clone https://github.com/arc53/DocsGPT.git`
#### Download the package information
Once it has finished cloning the repository, it is time to download the package information from all sources. To do so simply enter the following command:
Once it has finished cloning the repository, it is time to download the package information from all sources. To do so, simply enter the following command:
`sudo apt update`
@@ -56,13 +49,13 @@ And now install docker-compose:
`sudo apt install docker-compose`
#### Access the DocsGPT folder
#### Access the DocsGPT Folder
Enter the following command to access the folder in which DocsGPT docker-compose file is present.
Enter the following command to access the folder in which the DocsGPT docker-compose file is present.
`cd DocsGPT/`
#### Prepare the environment
#### Prepare the Environment
Inside the DocsGPT folder create a `.env` file and copy the contents of `.env_sample` into it.
@@ -78,16 +71,16 @@ SELF_HOSTED_MODEL=false
To save the file, press CTRL+X, then Y, and then ENTER.
Next, we need to set a correct IP for our Backend. To do so, open the docker-compose.yml file:
Next, set the correct IP for the Backend by opening the docker-compose.yml file:
`nano docker-compose.yml`
And change this line 7 `VITE_API_HOST=http://localhost:7091`
And Change line 7 to: `VITE_API_HOST=http://localhost:7091`
to this `VITE_API_HOST=http://<your instance public IP>:7091`
This will allow the frontend to connect to the backend.
#### Running the app
#### Running the Application
You're almost there! Now that all the necessary bits and pieces have been installed, it is time to run the application. To do so, use the following command:
@@ -97,16 +90,19 @@ Launching it for the first time will take a few minutes to download all the nece
Once this is done you can go ahead and close the terminal window.
#### Enabling ports
#### Enabling Ports
Before you are able to access your live instance, you must first enable the port that it is using.
a. Before you are able to access your live instance, you must first enable the port that it is using.
Open your Lightsail instance and head to "Networking".
b. Open your Lightsail instance and head to "Networking".
Then click on "Add rule" under "IPv4 Firewall", enter `5173` as your port, and hit "Create".
c. Then click on "Add rule" under "IPv4 Firewall", enter `5173` as your port, and hit "Create".
Repeat the process for port `7091`.
#### Access your instance
Your instance will now be available under your Public IP Address and port `5173`. Enjoy!
Your instance is now available at your Public IP Address on port 5173. Enjoy using DocsGPT!
## Other Deployment Options
- [Deploy DocsGPT on Civo Compute Cloud](https://dev.to/rutamhere/deploying-docsgpt-on-civo-compute-c)

101
docs/pages/Deploying/Quickstart.md
View File

@@ -1,24 +1,107 @@
## Launching Web App
Note: Make sure you have Docker installed
**Note**: Make sure you have Docker installed
On Mac OS or Linux just write:
**On macOS or Linux:**
Just run the following command::
`./setup.sh`
It will install all the dependencies and give you an option to download the local model or use OpenAI
This command will install all the necessary dependencies and provide you with an option to download the local model or use OpenAI.
Otherwise, refer to this Guide:
If you prefer to follow manual steps, refer to this guide:
1. Open and download this repository with `git clone https://github.com/arc53/DocsGPT.git`.
2. Create a `.env` file in your root directory and set your `API_KEY` with your [OpenAI api key](https://platform.openai.com/account/api-keys).
3. Run `docker-compose build && docker-compose up`.
1. Open and download this repository with
`git clone https://github.com/arc53/DocsGPT.git`.
2. Create a `.env` file in your root directory and set your `API_KEY` with your [OpenAI API key](https://platform.openai.com/account/api-keys).
3. Run the following commands:
`docker-compose build && docker-compose up`.
4. Navigate to `http://localhost:5173/`.
To stop just run `Ctrl + C`.
To stop, simply press Ctrl + C.
**For WINDOWS:**
To run the setup on Windows, you have two options: using the Windows Subsystem for Linux (WSL) or using Git Bash or Command Prompt.
**Option 1: Using Windows Subsystem for Linux (WSL):**
1. Install WSL if you haven't already. You can follow the official Microsoft documentation for installation: (https://learn.microsoft.com/en-us/windows/wsl/install).
2. After setting up WSL, open the WSL terminal.
3. Clone the repository and create the `.env` file:
```
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
echo "API_KEY=Yourkey" > .env
echo "VITE_API_STREAMING=true" >> .env
```
4. Run the following command to start the setup with Docker Compose:
`./run-with-docker-compose.sh`
5. Open your web browser and navigate to (http://localhost:5173/).
6. To stop the setup, just press `Ctrl + C` in the WSL terminal
**Option 2: Using Git Bash or Command Prompt (CMD):**
1. Install Git for Windows if you haven't already. Download it from the official website: (https://gitforwindows.org/).
2. Open Git Bash or Command Prompt.
3. Clone the repository and create the `.env` file:
```
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
echo "API_KEY=Yourkey" > .env
echo "VITE_API_STREAMING=true" >> .env
```
4.Run the following command to start the setup with Docker Compose:
`./run-with-docker-compose.sh`
5.Open your web browser and navigate to (http://localhost:5173/).
6.To stop the setup, just press Ctrl + C in the Git Bash or Command Prompt terminal.
These steps should help you set up and run the project on Windows using either WSL or Git Bash/Command Prompt.
**Important:** Ensure that Docker is installed and properly configured on your Windows system for these steps to work.
For WINDOWS:
To run the given setup on Windows, you can use the Windows Subsystem for Linux (WSL) or a Git Bash terminal to execute similar commands. Here are the steps adapted for Windows:
Option 1: Using Windows Subsystem for Linux (WSL):
1. Install WSL if you haven't already. You can follow the official Microsoft documentation for installation: (https://learn.microsoft.com/en-us/windows/wsl/install).
2. After setting up WSL, open the WSL terminal.
3. Clone the repository and create the `.env` file:
```
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
echo "API_KEY=Yourkey" > .env
echo "VITE_API_STREAMING=true" >> .env
```
4. Run the following command to start the setup with Docker Compose:
`./run-with-docker-compose.sh`
5. Open your web browser and navigate to (http://localhost:5173/).
6. To stop the setup, just press `Ctrl + C` in the WSL terminal
Option 2: Using Git Bash or Command Prompt (CMD):
1. Install Git for Windows if you haven't already. You can download it from the official website: (https://gitforwindows.org/).
2. Open Git Bash or Command Prompt.
3. Clone the repository and create the `.env` file:
```
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT
echo "API_KEY=Yourkey" > .env
echo "VITE_API_STREAMING=true" >> .env
```
4.Run the following command to start the setup with Docker Compose:
`./run-with-docker-compose.sh`
5.Open your web browser and navigate to (http://localhost:5173/).
6.To stop the setup, just press Ctrl + C in the Git Bash or Command Prompt terminal.
These steps should help you set up and run the project on Windows using either WSL or Git Bash/Command Prompt. Make sure you have Docker installed and properly configured on your Windows system for this to work.
### Chrome Extension
To install the Chrome extension:
#### Installing the Chrome extension:
To enhance your DocsGPT experience, you can install the DocsGPT Chrome extension. Here's how:
1. In the DocsGPT GitHub repository, click on the "Code" button and select "Download ZIP".
2. Unzip the downloaded file to a location you can easily access.

120
docs/pages/Developing/API-docs.md
View File

@@ -1,9 +1,25 @@
Currently, the application provides the following main API endpoints:
# API Endpoints Documentation
### /api/answer
It's a POST request that sends a JSON in body with 4 values. It will receive an answer for a user provided question.
Here is a JavaScript fetch example:
*Currently, the application provides the following main API endpoints:*
### 1. /api/answer
**Description:**
This endpoint is used to request answers to user-provided questions.
**Request:**
Method: POST
Headers: Content-Type should be set to "application/json; charset=utf-8"
Request Body: JSON object with the following fields:
* **question:** The user's question
* **history:** (Optional) Previous conversation history
* **api_key:** Your API key
* **embeddings_key:** Your embeddings key
* **active_docs:** The location of active documentation
Here is a JavaScript Fetch Request example:
```js
// answer (POST http://127.0.0.1:5000/api/answer)
fetch("http://127.0.0.1:5000/api/answer", {
@@ -18,8 +34,9 @@ fetch("http://127.0.0.1:5000/api/answer", {
.then(console.log.bind(console))
```
In response you will get a json document like this one:
**Response**
In response, you will get a JSON document containing the answer,query and the result:
```json
{
"answer": " Hi there! How can I help you?\n",
@@ -28,10 +45,17 @@ In response you will get a json document like this one:
}
```
### /api/docs_check
It will make sure documentation is loaded on a server (just run it every time user is switching between libraries (documentations)).
It's a POST request that sends a JSON in body with 1 value. Here is a JavaScript fetch example:
### 2. /api/docs_check
**Description:**
This endpoint will make sure documentation is loaded on the server (just run it every time user is switching between libraries (documentations)).
**Request:**
Headers: Content-Type should be set to "application/json; charset=utf-8"
Request Body: JSON object with the field:
* **docs:** The location of the documentation
```js
// answer (POST http://127.0.0.1:5000/api/docs_check)
fetch("http://127.0.0.1:5000/api/docs_check", {
@@ -45,7 +69,9 @@ fetch("http://127.0.0.1:5000/api/docs_check", {
.then(console.log.bind(console))
```
In response you will get a json document like this one:
**Response:**
In response, you will get a JSON document like this one indicating whether the documentation exists or not.:
```json
{
"status": "exists"
@@ -53,18 +79,36 @@ In response you will get a json document like this one:
```
### /api/combine
Provides json that tells UI which vectors are available and where they are located with a simple get request.
### 3. /api/combine
**Description:**
This endpoint provides information about available vectors and their locations with a simple GET request.
**Request:**
Method: GET
**Response:**
Response will include:
`date`, `description`, `docLink`, `fullName`, `language`, `location` (local or docshub), `model`, `name`, `version`.
Example of json in Docshub and local:
Example of JSON in Docshub and local:
<img width="295" alt="image" src="https://user-images.githubusercontent.com/15183589/224714085-f09f51a4-7a9a-4efb-bd39-798029bb4273.png">
### /api/upload
Uploads file that needs to be trained, response is json with task id, which can be used to check on tasks progress
### 4. /api/upload
**Description:**
This endpoint is used to upload a file that needs to be trained, response is JSON with task ID, which can be used to check on task's progress.
**Request:**
Method: POST
Request Body: A multipart/form-data form with file upload and additional fields, including "user" and "name."
HTML example:
```html
@@ -79,20 +123,24 @@ HTML example:
</form>
```
Response:
```json
{
"status": "ok",
"task_id": "b2684988-9047-428b-bd47-08518679103c"
}
**Response:**
```
JSON response with a status and a task ID that can be used to check the task's progress.
### /api/task_status
Gets task status (`task_id`) from `/api/upload`:
### 5. /api/task_status
**Description:**
This endpoint is used to get the status of a task (`task_id`) from `/api/upload`
**Request:**
Method: GET
Query Parameter: task_id (task ID to check)
**Sample JavaScript Fetch Request:**
```js
// Task status (Get http://127.0.0.1:5000/api/task_status)
fetch("http://localhost:5001/api/task_status?task_id=b2d2a0f4-387c-44fd-a443-e4fe2e7454d1", {
fetch("http://localhost:5001/api/task_status?task_id=YOUR_TASK_ID", {
"method": "GET",
"headers": {
"Content-Type": "application/json; charset=utf-8"
@@ -102,9 +150,12 @@ fetch("http://localhost:5001/api/task_status?task_id=b2d2a0f4-387c-44fd-a443-e4f
.then(console.log.bind(console))
```
Responses:
**Response:**
There are two types of responses:
1. while task it still running, where "current" will show progress from 0 to 100
1. While the task is still running, the 'current' value will show progress from 0 to 100.
```json
{
"result": {
@@ -114,7 +165,7 @@ There are two types of responses:
}
```
2. When task is completed
2. When task is completed:
```json
{
"result": {
@@ -132,8 +183,14 @@ There are two types of responses:
}
```
### /api/delete_old
Deletes old vectorstores:
### 6. /api/delete_old
**Description:**
This endpoint is used to delete old Vector Stores.
**Request:**
Method: GET
```js
// Task status (GET http://127.0.0.1:5000/api/docs_check)
fetch("http://localhost:5001/api/task_status?task_id=b2d2a0f4-387c-44fd-a443-e4fe2e7454d1", {
@@ -144,10 +201,11 @@ fetch("http://localhost:5001/api/task_status?task_id=b2d2a0f4-387c-44fd-a443-e4f
})
.then((res) => res.text())
.then(console.log.bind(console))
```
**Response:**
Response:
JSON response indicating the status of the operation.
```json
{ "status": "ok" }
```

55
docs/pages/Extensions/Chatwoot-extension.md
View File

@@ -1,29 +1,42 @@
### To start chatwoot extension:
1. Prepare and start the DocsGPT itself (load your documentation too). Follow our [wiki](https://github.com/arc53/DocsGPT/wiki) to start it and to [ingest](https://github.com/arc53/DocsGPT/wiki/How-to-train-on-other-documentation) data.
2. Go to chatwoot, **Navigate** to your profile (bottom left), click on profile settings, scroll to the bottom and copy **Access Token**.
3. Navigate to `/extensions/chatwoot`. Copy `.env_sample` and create `.env` file.
4. Fill in the values.
### To Start Chatwoot Extension:
```
docsgpt_url=<docsgpt_api_url>
chatwoot_url=<chatwoot_url>
docsgpt_key=<openai_api_key or other llm key>
chatwoot_token=<from part 2>
```
1. **Prepare and Start DocsGPT:**
- Launch DocsGPT using the instructions in our [wiki](https://github.com/arc53/DocsGPT/wiki).
- Make sure to load your documentation.
5. Start with `flask run` command.
2. **Get Access Token from Chatwoot:**
- Navigate to Chatwoot.
- Go to your profile (bottom left), click on profile settings.
- Scroll to the bottom and copy the **Access Token**.
If you want for bot to stop responding to questions for a specific user or session just add label `human-requested` in your conversation.
3. **Set Up Chatwoot Extension:**
- Navigate to `/extensions/chatwoot`.
- Copy `.env_sample` and create a `.env` file.
- Fill in the values in the `.env` file:
```env
docsgpt_url=<docsgpt_api_url>
chatwoot_url=<chatwoot_url>
docsgpt_key=<openai_api_key or other llm key>
chatwoot_token=<from part 2>
```
### Optional (extra validation)
In `app.py` uncomment lines 12-13 and 71-75
4. **Start the Extension:**
- Use the command `flask run` to start the extension.
in your `.env` file add:
5. **Optional: Extra Validation**
- In `app.py`, uncomment lines 12-13 and 71-75.
- Add the following lines to your `.env` file:
```
account_id=(optional) 1
assignee_id=(optional) 1
```
```env
account_id=(optional) 1
assignee_id=(optional) 1
```
Those are chatwoot values and will allow you to check if you are responding to correct widget and responding to questions assigned to specific user.
These Chatwoot values help ensure you respond to the correct widget and handle questions assigned to a specific user.
### Stopping Bot Responses for Specific User or Session:
- If you want the bot to stop responding to questions for a specific user or session, add a label `human-requested` in your conversation.
### Additional Notes:
- For further details on training on other documentation, refer to our [wiki](https://github.com/arc53/DocsGPT/wiki/How-to-train-on-other-documentation).

10
docs/pages/Extensions/react-widget.md
View File

@@ -4,7 +4,7 @@
Got to your project and install a new dependency: `npm install docsgpt`.
### Usage
Go to your project and in the file where you want to use the widget import it:
Go to your project and in the file where you want to use the widget, import it:
```js
import { DocsGPTWidget } from "docsgpt";
import "docsgpt/dist/style.css";
@@ -14,12 +14,12 @@ import "docsgpt/dist/style.css";
Then you can use it like this: `<DocsGPTWidget />`
DocsGPTWidget takes 3 props:
- `apiHost` — url of your DocsGPT API.
- `selectDocs` — documentation that you want to use for your widget (eg. `default` or `local/docs1.zip`).
- `apiKey` — usually its empty.
- `apiHost` — URL of your DocsGPT API.
- `selectDocs` — documentation that you want to use for your widget (e.g. `default` or `local/docs1.zip`).
- `apiKey` — usually it's empty.
### How to use DocsGPTWidget with [Nextra](https://nextra.site/) (Next.js + MDX)
Install you widget as described above and then go to your `pages/` folder and create a new file `_app.js` with the following content:
Install your widget as described above and then go to your `pages/` folder and create a new file `_app.js` with the following content:
```js
import { DocsGPTWidget } from "docsgpt";
import "docsgpt/dist/style.css";

3
docs/pages/Guides/Customising-prompts.md
View File

@@ -17,8 +17,7 @@ When using code examples, use the following format:
(code)
{summaries}
Thank you
```

20
docs/pages/Guides/How-to-train-on-other-documentation.md
View File

@@ -5,18 +5,18 @@ This AI can use any documentation, but first it needs to be prepared for similar
Start by going to `/scripts/` folder.
If you open this file you will see that it uses RST files from the folder to create a `index.faiss` and `index.pkl`.
If you open this file, you will see that it uses RST files from the folder to create a `index.faiss` and `index.pkl`.
It currently uses OPEN_AI to create vector store, so make sure your documentation is not too big. Pandas cost me around 3-4$.
It currently uses OPEN_AI to create the vector store, so make sure your documentation is not too big. Pandas cost me around $3-$4.
You can usually find documentation on github in `docs/` folder for most open-source projects.
You can usually find documentation on Github in `docs/` folder for most open-source projects.
### 1. Find documentation in .rst/.md and create a folder with it in your scripts directory
Name it `inputs/`
Put all your .rst/.md files in there
The search is recursive, so you don't need to flatten them
- Name it `inputs/`
- Put all your .rst/.md files in there
- The search is recursive, so you don't need to flatten them
If there are no .rst/.md files just convert whatever you find to txt and feed it. (don't forget to change the extension in script)
If there are no .rst/.md files just convert whatever you find to .txt and feed it. (don't forget to change the extension in script)
### 2. Create .env file in `scripts/` folder
And write your OpenAI API key inside
@@ -32,7 +32,7 @@ It will tell you how much it will cost
### 5. Run web app
Once you run it will use new context that is relevant to your documentation
Once you run it will use new context that is relevant to your documentation
Make sure you select default in the dropdown in the UI
## Customization
@@ -41,7 +41,7 @@ You can learn more about options while running ingest.py by running:
`python ingest.py --help`
| Options | |
|:--------------------------------:|:------------------------------------------------------------------------------------------------------------------------------:|
| **ingest** | Runs 'ingest' function converting documentation to Faiss plus Index format |
| **ingest** | Runs 'ingest' function, converting documentation to Faiss plus Index format |
| --dir TEXT | List of paths to directory for index creation. E.g. --dir inputs --dir inputs2 [default: inputs] |
| --file TEXT | File paths to use (Optional; overrides directory) E.g. --files inputs/1.md --files inputs/2.md |
| --recursive / --no-recursive | Whether to recursively search in subdirectories [default: recursive] |
@@ -56,4 +56,4 @@ You can learn more about options while running ingest.py by running:
| | |
| **convert** | Creates documentation in .md format from source code |
| --dir TEXT | Path to a directory with source code. E.g. --dir inputs [default: inputs] |
| --formats TEXT | Source code language from which to create documentation. Supports py, js and java. E.g. --formats py [default: py] |
| --formats TEXT | Source code language from which to create documentation. Supports py, js and java. E.g. --formats py [default: py] |

10
docs/pages/Guides/How-to-use-different-LLM.md
View File

@@ -1,4 +1,4 @@
Fortunately there are many providers for LLM's and some of them can even be ran locally
Fortunately, there are many providers for LLM's and some of them can even be run locally
There are two models used in the app:
1. Embeddings.
@@ -21,12 +21,16 @@ By default, we use OpenAI's models but if you want to change it or even run it l
You don't need to provide keys if you are happy with users providing theirs, so make sure you set `LLM_NAME` and `EMBEDDINGS_NAME`.
Options:
LLM_NAME (openai, manifest, cohere, Arc53/docsgpt-14b, Arc53/docsgpt-7b-falcon)
LLM_NAME (openai, manifest, cohere, Arc53/docsgpt-14b, Arc53/docsgpt-7b-falcon, llama.cpp)
EMBEDDINGS_NAME (openai_text-embedding-ada-002, huggingface_sentence-transformers/all-mpnet-base-v2, huggingface_hkunlp/instructor-large, cohere_medium)
If using Llama, set the `EMBEDDINGS_NAME` to `huggingface_sentence-transformers/all-mpnet-base-v2` and be sure to download [this model](https://d3dg1063dc54p9.cloudfront.net/models/docsgpt-7b-f16.gguf) into the `models/` folder: `https://d3dg1063dc54p9.cloudfront.net/models/docsgpt-7b-f16.gguf`.
Alternatively, if you wish to run Llama locally, you can run `setup.sh` and choose option 1 when prompted. You do not need to manually add the DocsGPT model mentioned above to your `models/` folder if you use `setup.sh`, as the script will manage that step for you.
That's it!
### Hosting everything locally and privately (for using our optimised open-source models)
If you are working with important data and don't want anything to leave your premises.
Make sure you set `SELF_HOSTED_MODEL` as true in you `.env` variable and for your `LLM_NAME` you can use anything that's on Hugging Face.
Make sure you set `SELF_HOSTED_MODEL` as true in your `.env` variable and for your `LLM_NAME` you can use anything that's on Hugging Face.

8
docs/pages/Guides/My-AI-answers-questions-using-external-knowledge.md
View File

@@ -1,10 +1,10 @@
If your AI uses external knowledge and is not explicit enough it is ok, because we try to make docsgpt friendly.
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.
But if you want to adjust it, here is a simple way:-
Got to `application/prompts/chat_combine_prompt.txt`
- Got to `application/prompts/chat_combine_prompt.txt`
And change it to
- And change it to
```