AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-14 05:36:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[doc] Updated default value of quote in 'get answers' (#1093)

Browse Source 
### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] Documentation Update
This commit is contained in:
writinwaters 2024-06-07 14:08:59 +08:00 committed by GitHub
parent d0951ee27b
commit 22468a8590
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docs/guides/deploy_local_llm.md
View File

@ -115,34 +115,38 @@ Xorbits Inference([Xinference](https://github.com/xorbitsai/inference)) enables
- For a complete list of supported models, see the [Builtin Models](https://inference.readthedocs.io/en/latest/models/builtin/). - For a complete list of supported models, see the [Builtin Models](https://inference.readthedocs.io/en/latest/models/builtin/).
::: :::
To deploy a local model, e.g., **Llama3**, using Xinference: To deploy a local model, e.g., **Mistral**, using Xinference:
### 1. Start an Xinference instance ### 1. Check firewall settings
Ensure that your host machine's firewall allows inbound connections on port 9997.
### 2. Start an Xinference instance
```bash ```bash
$ xinference-local --host 0.0.0.0 --port 9997 $ xinference-local --host 0.0.0.0 --port 9997
``` ```
### 2. Launch your local model ### 3. Launch your local model
Launch your local model (**Mistral**), ensuring that you replace `${quantization}` with your chosen quantization method Launch your local model (**Mistral**), ensuring that you replace `${quantization}` with your chosen quantization method
: :
```bash ```bash
$ xinference launch -u mistral --model-name mistral-v0.1 --size-in-billions 7 --model-format pytorch --quantization ${quantization} $ xinference launch -u mistral --model-name mistral-v0.1 --size-in-billions 7 --model-format pytorch --quantization ${quantization}
``` ```
### 3. Add Xinference ### 4. Add Xinference
In RAGFlow, click on your logo on the top right of the page **>** **Model Providers** and add Xinference to RAGFlow: In RAGFlow, click on your logo on the top right of the page **>** **Model Providers** and add Xinference to RAGFlow:
![add xinference](https://github.com/infiniflow/ragflow/assets/93570324/10635088-028b-4b3d-add9-5c5a6e626814) ![add xinference](https://github.com/infiniflow/ragflow/assets/93570324/10635088-028b-4b3d-add9-5c5a6e626814)
### 4. Complete basic Xinference settings ### 5. Complete basic Xinference settings
Enter an accessible base URL, such as `http://<your-xinference-endpoint-domain>:9997/v1`. Enter an accessible base URL, such as `http://<your-xinference-endpoint-domain>:9997/v1`.
### 5. Update System Model Settings ### 6. Update System Model Settings
Click on your logo **>** **Model Providers** **>** **System Model Settings** to update your model: Click on your logo **>** **Model Providers** **>** **System Model Settings** to update your model.
*You should now be able to find **mistral** from the dropdown list under **Chat model**.* *You should now be able to find **mistral** from the dropdown list under **Chat model**.*

2
docs/references/api.md
View File

@ -224,7 +224,7 @@ This method retrieves from RAGFlow the answer to the user's latest question.
|------------------|--------|----------|---------------| |------------------|--------|----------|---------------|
| `conversation_id`| string | Yes | The ID of the conversation session. Call ['GET' /new_conversation](#create-conversation) to retrieve the ID.| | `conversation_id`| string | Yes | The ID of the conversation session. Call ['GET' /new_conversation](#create-conversation) to retrieve the ID.|
| `messages` | json | Yes | The latest question in a JSON form, such as `[{"role": "user", "content": "How are you doing!"}]`| | `messages` | json | Yes | The latest question in a JSON form, such as `[{"role": "user", "content": "How are you doing!"}]`|
| `quote` | bool | No | Default: true | | `quote` | bool | No | Default: false|
| `stream` | bool | No | Default: true | | `stream` | bool | No | Default: true |
| `doc_ids` | string | No | Document IDs delimited by comma, like `c790da40ea8911ee928e0242ac180005,23dsf34ree928e0242ac180005`. The retrieved contents will be confined to these documents. | | `doc_ids` | string | No | Document IDs delimited by comma, like `c790da40ea8911ee928e0242ac180005,23dsf34ree928e0242ac180005`. The retrieved contents will be confined to these documents. |