### What problem does this PR solve?

Add Zhipu GLM-4.5 model series. #9708.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

add ZhipuAI GLM-4.5 model series

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Refactor OpenAI to enable audio parsing.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

### What problem does this PR solve?

Fix Gemini parameters error.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

Supports GPT-5.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add Claude Opus 4.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring

### What problem does this PR solve?

Add a series of qwen3 latest SOTA models:
qwen3-coder-480b-a35b-instruct, qwen3-30b-a3b-instruct-2507,
qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-instruct-2507,
qwen3-235b-a22b-thinking-2507
### Type of change
- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Fix kimi-latest is not authorized.

Add kimi-thinking-preview.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Support 302.AI provider.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

add Kimi-K2-Instruct from Tongyi-Qianwen API

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add model provider DeepInfra. This model list comes from our community. 

NOTE: most endpoints haven't been tested, but they should work as OpenAI
does.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Adds configurations for gemini-2.5-flash and Gemini 2.5-pro models,
including tags, maximum token limits, and model types.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Add Kimi model series support.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
This PR enhances the application's capabilities by adding support for
four new Voyage embedding models (voyage-3-large, voyage-3.5,
voyage-3.5-lite, and voyage-code-3) to the `llm_factories.json`
configuration file. These models expand the available options for text
embedding tasks, enabling improved processing of text data with a
maximum token limit of 32,000. This addition addresses the need for more
diverse and specialized embedding models to support various use cases
without altering existing functionality.

### Type of change
- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add xAI provider (experimental feature, requires user feedback).

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add Qwen3-Embedding text-embedding-v4.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Add voyage-multimodal-3.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Update gemini2.5

### Type of change

- [x] Refactoring

### What problem does this PR solve?

Add claude4 models.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

change default models to buildin models
https://github.com/infiniflow/ragflow/issues/7774

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### 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] Other (please describe): llm factories update

### What problem does this PR solve?

Adds support for the GPT-4.1 series from OpenAI.

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
fix deepseek-ai/deepseek-vl2 model can not be select as a VL model to
parse pdf image . And add other vl models config from siliconflow
_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] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

---------

Co-authored-by: unknown <taoshi.ln@chinatelecom.cn>

### What problem does this PR solve?

Qwen3 and more LLMs.

Close #7296

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

Replace models of novita

### Type of change

- [x] Other (please describe): Replace models of novita

With current config will get error "Fail to access model(gemma-7b-it)
using this api key"
Since the model has been removed, according to Groq official document:
https://console.groq.com/docs/models

### Type of change

- [ x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Update LLM models

### Type of change

- [x] Refactoring

### What problem does this PR solve?

#6733

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#6697

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

### Type of change

- [x] Refactoring
- [x] Performance Improvement

### What problem does this PR solve?

#6577

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?



### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Chenzy <chenzy901@gmail.com>

### What problem does this PR solve?

#6421

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

AWS Bedrock has made deepseek-r1 available on its serverless inference.

This adds the R1 serverless model for use via the bedrock model
abilities.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

add qwq model support to Tongyi-Qianwen factory
https://github.com/infiniflow/ragflow/issues/5869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)


![image](https://github.com/user-attachments/assets/49f5c6a0-ecaf-41dd-a23a-2009f854d62c)


![image](https://github.com/user-attachments/assets/93ffa303-920e-4942-8188-bcd6b7209204)


![1741774779](https://github.com/user-attachments/assets/25f2fd1d-8640-4df0-9a08-78ee9daaa8fe)


![image](https://github.com/user-attachments/assets/4763cf6c-1f76-43c4-80ee-74dfd666a184)

Co-authored-by: zhaozhicheng <zhicheng.zhao@fastonetech.com>

### What problem does this PR solve?

#5806

### Type of change


- [x] Refactoring

### What problem does this PR solve?

#5782

### Type of change

- [x] Refactoring

### What problem does this PR solve?

#5658

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

LLM library update

### Type of change

- [x] Other : config update

### What problem does this PR solve?

Read to add VLMM.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

This PR supports downloading models from ModelScope. The main
modifications are as follows:
-New Feature (non-breaking change which adds functionality)
-Documentation Update

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

The current design is not well-suited for multimodal models, as each
model can only be configured for a single purpose—either chat or
Img2txt. To work around this limitation, we use model aliases such as
gpt-4o-mini and gpt-4o-mini-2024-07-18.

To fix this, this PR allows specifying the Img2txt model by tag instead
of model_type.

### Type of change
- [x] Refactoring

### What problem does this PR solve?

Add a LLM provider: PPIO

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update

add gemini-2.0-flash-thinking-exp-01-21

### What problem does this PR solve?

#4870 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#4870

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#4761

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#4751

### Type of change

- [x] New Feature (non-breaking change which adds functionality)