Commit Graph

422 Commits

Author SHA1 Message Date
915e385244 Fix: uv lock updates (#11511)
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 16:01:12 +08:00
bcd70affb5 Fix: unexpected parameter. (#11497)
### What problem does this PR solve?

#11489

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-25 11:17:27 +08:00
174a2578e8 Feat: add auth header for Ollama chat model (#11452)
### What problem does this PR solve?

Add auth header for Ollama chat model. #11350

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-21 19:47:06 +08:00
1c06ec39ca fix cohere rerank base_url default (#11353)
### What problem does this PR solve?

**Cohere rerank base_url default handling**

- Background: When no rerank base URL is configured, the settings
pipeline was passing an empty string through RERANK_CFG →
TenantLLMService → CoHereRerank, so the Cohere client received
base_url="" and produced “missing protocol” errors during rerank calls.

- What changed: The CoHereRerank constructor now only forwards base_url
to the Cohere client when it isn’t empty/whitespace, causing the client
to fall back to its default API endpoint otherwise.

- Why it matters: This prevents invalid URL construction in the rerank
workflow and keeps tests/sanity checks that rely on the default Cohere
endpoint from failing when no custom base URL is specified.

### Type of change

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

Co-authored-by: Philipp Heyken Soares <philipp.heyken-soares@am.ai>
2025-11-20 09:46:39 +08:00
e8fe580d7a Feat: add Gemini 3 Pro preview (#11361)
### What problem does this PR solve?

Add Gemini 3 Pro preview.

Change `GenerativeModel` to `genai`.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-19 13:17:22 +08:00
0db00f70b2 Fix: add describe_image_with_prompt for ZHIPU AI (#11317)
### What problem does this PR solve?

Fix: add describe_image_with_prompt for ZHIPU AI  #11289 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-18 13:09:39 +08:00
3fcf2ee54c feat: add new LLM provider Jiekou.AI (#11300)
### 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] New Feature (non-breaking change which adds functionality)

Co-authored-by: Jason <ggbbddjm@gmail.com>
2025-11-17 19:47:46 +08:00
bd4bc57009 Refactor: move mcp connection utilities to common (#11304)
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-17 15:34:17 +08:00
f441f8ffc2 Fix: waitForResponse component. (#11172)
### What problem does this PR solve?

#10056

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2025-11-11 16:58:47 +08:00
dd5b8e2e1a Fix: add auto_parse to kb detail. (#11153)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-11 12:22:43 +08:00
68b952abb1 Don't select vector on infinity (#11151)
### What problem does this PR solve?

Don't select vector on infinity

### Type of change

- [x] Performance Improvement
2025-11-10 18:01:40 +08:00
82ca2e0378 Refactor: QWenCV release temp path (#11122)
### What problem does this PR solve?

QWenCV release temp path

### Type of change
- [x] Refactoring
2025-11-10 10:15:37 +08:00
660386d3b5 Fix: cannot parse images (#11044)
### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/11043

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-10 09:31:19 +08:00
9fcc4946e2 Feat: add kimi-k2-thinking and moonshot-v1-vision-preview (#11110)
### What problem does this PR solve?

Add kimi-k2-thinking and moonshot-v1-vision-preview.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-11-07 19:52:57 +08:00
f98b24c9bf Move api.settings to common.settings (#11036)
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-06 09:36:38 +08:00
1a9215bc6f Move some vars to globals (#11017)
### What problem does this PR solve?

As title.

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-05 14:14:38 +08:00
96c015fb85 Fix and refactor imports (#11010)
### What problem does this PR solve?

1. Move EMBEDDING_CFG to common.globals
2. Fix error imports
3. Move signal handles to common/signal_utils.py

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-05 11:07:54 +08:00
378bdfccfc Refactor log utils (#10973)
### What problem does this PR solve?

As title.

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-03 20:25:02 +08:00
2d83c64eed Fix:wrong describe_with_prompt() in ollama (#10963)
### What problem does this PR solve?

change:
wrong describe_with_prompt() in ollama

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-11-03 19:16:41 +08:00
360f5c1179 Move token related functions to common (#10942)
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-11-03 08:50:05 +08:00
fe4852cb71 TEI auto truncate inputs (#10916)
### What problem does this PR solve?

TEI auto truncate inputs

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-10-31 16:46:20 +08:00
0ecccd27eb Refactor:improve the logic for rerank models to cal the total token count (#10882)
### What problem does this PR solve?

improve the logic for rerank models to cal the total token count

### Type of change

- [x] Refactoring
2025-10-31 09:46:16 +08:00
c0c2a10680 Feat: allow initialize Redis without password (#10856)
### What problem does this PR solve?

Allow initialize Redis without password.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-29 09:45:28 +08:00
d86d7061ea Refactor: Improve how to get total token count for AnthropicCV (#10658)
### What problem does this PR solve?

 Improve how to get total token count for AnthropicCV

### Type of change

- [x] Refactoring
2025-10-29 09:41:15 +08:00
84d1ffe44c Feature/add new models for token pony and bug fix for use llm (#10823)
new models for token pony and bug fix for use llm

Co-authored-by: huangzl <huangzl@shinemo.com>
2025-10-28 10:04:41 +08:00
3bd0b99495 Fix: gemini cv model chat issue. (#10799)
### What problem does this PR solve?

#10787
#10781

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-10-27 11:43:56 +08:00
73144e278b Don't release full image (#10654)
### What problem does this PR solve?

Introduced gpu profile in .env
Added Dockerfile_tei
fix datrie
Removed LIGHTEN flag

### Type of change

- [x] Documentation Update
- [x] Refactoring
2025-10-23 23:02:27 +08:00
b30f0be858 Refactor: How LiteLLMBase Calculate total count (#10532)
### What problem does this PR solve?

How LiteLLMBase Calculate total count

### Type of change

- [x] Refactoring
2025-10-22 12:25:31 +08:00
a82e9b3d91 Fix: can't upload image in ollama model #10447 (#10717)
### What problem does this PR solve?

Fix: can't upload image in ollama model #10447

### Type of change

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


### Change all `image=[]` to `image = None`

Changing `image=[]` to `images=None` avoids Python’s mutable default
parameter issue.
If you keep `images=[]`, all calls share the same list, so modifying it
(e.g., images.append()) will affect later calls.
Using images=None and creating a new list inside the function ensures
each call is independent.
This change does not affect current behavior — it simply makes the code
safer and more predictable.


把 `images=[]` 改成 `images=None` 是为了避免 Python 默认参数的可变对象问题。
如果保留 `images=[]`,所有调用都会共用同一个列表,一旦修改就会影响后续调用。
改成 None 并在函数内部重新创建列表,可以确保每次调用都是独立的。
这个修改不会影响现有运行结果,只是让代码更安全、更可控。
2025-10-22 12:24:12 +08:00
aaa4776657 Feat: Qwen-VL series supports video parsing (#10676)
### What problem does this PR solve?

Qwen-VL series supports video parsing. #10617.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-21 09:36:13 +08:00
5b2e5dd334 Feat: Gemini supports video parsing (#10671)
### What problem does this PR solve?

Gemini supports video parsing.


![img_v3_02r8_adbd5adc-d665-4756-9a00-3ae0f12224fg](https://github.com/user-attachments/assets/30d8d296-c336-4b55-9823-803979e705ca)


![img_v3_02r8_ab60c046-1727-4029-ad2e-66097fd3ccbg](https://github.com/user-attachments/assets/441b1487-a970-427e-98b6-6e1e002f2bad)

Close: #10617

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-20 16:49:47 +08:00
b15643bd80 Feat:VolcEngine Model type add IMAGE2TEXT (#10629)
### What problem does this PR solve?
issue:
[#9004](https://github.com/infiniflow/ragflow/issues/9004)
change:
VolcEngine Model type add IMAGE2TEXT

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-17 11:43:22 +08:00
4e86ee4ff9 Feat: Support Specifying OpenRouter Model Provider (#10550)
### What problem does this PR solve?
issue:
[#5787](https://github.com/infiniflow/ragflow/issues/5787)
change:
Support Specifying OpenRouter Model Provider

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-16 09:39:59 +08:00
5037a28e4d Fix problem with Google Cloud models with reasoning (like gemini) - Additional fix to issue #10474 (#10502)
### What problem does this PR solve?

Issue #10474  -  Update to PR #10477 

### Type of change

- [X] Bug Fix (non-breaking change which fixes an issue)
2025-10-15 14:54:20 +08:00
9e73f799b2 Feat: add Zhipu GLM-ASR model (#10529)
### What problem does this PR solve?

Add Zhipu GLM-ASR model

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-14 09:32:45 +08:00
fee757eb41 Fix: Disable reasoning on Gemini 2.5 Flash by default (#10477)
### What problem does this PR solve?

Gemini 2.5 Flash Models use reasoning by default. There is currently no
way to disable this behaviour. This leads to very long response times (>
1min). The default behaviour should be, that reasoning is disabled and
configurable

issue #10474 

### Type of change

- [X] Bug Fix (non-breaking change which fixes an issue)
2025-10-11 10:22:51 +08:00
0283e4098f Fix #10408 (#10471)
### What problem does this PR solve?

Google Cloud model does not work correctly with gemini-2.5 models
Close #10408

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-10-10 19:18:24 +08:00
0d8791936e Feat: TOC retrieval (#10456)
### What problem does this PR solve?

#10436

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-10 17:07:55 +08:00
5d167cd772 feat: support qwq reasoning models with non-stream output (#10468)
### What problem does this PR solve?
issue:
[#6193](https://github.com/infiniflow/ragflow/issues/6193)
change:
support qwq reasoning models with non-stream output

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-10 16:38:04 +08:00
6ab4c1a6e9 Refactor: improve how NvidiaCV calculate res total token counts (#10455)
### What problem does this PR solve?
improve how NvidiaCV calculate res total token counts

### Type of change
- [x] Refactoring
2025-10-10 11:03:40 +08:00
1a47e136e3 Feat: Adds a new feature that enables the LLM to extract a structured table of contents (TOC) directly from plain text. (#10428)
### What problem does this PR solve?

**Adds a new feature that enables the LLM to extract a structured table
of contents (TOC) directly from plain text.**
_This implementation prioritizes efficiency over reasoning — the model
runs in a strictly deterministic mode (thinking disabled) to minimize
latency.
As a result, overall performance may be less optimal, but the extraction
speed and consistency are guaranteed._

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-10-09 13:47:31 +08:00
cbf04ee470 Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)
### What problem does this PR solve?

#9869

### Type of change

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

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
dfc5fa1f4d Feat: add DeerAPI support (#10303)
### Related issues
#10078 

### What problem does this PR solve?
Integrate DeerAPI provider.

### Type of change

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

Co-authored-by: DeerAPI <tensor.null@gmail.com>
2025-10-09 11:14:49 +08:00
4585edc20e Refactor: improve cv model logics (#10414)
1. improve how to get total token count

Improve how to get total token count

### Type of change
- [x] Refactoring
2025-10-09 09:47:36 +08:00
17757930a3 Feat: add support for international Dashscope service (#10356)
### What problem does this PR solve?

 Add support for international Dashscope service. #10340 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-09-29 14:49:45 +08:00
ef59c5bab9 FIX: Rename the CometEmbed and CometSeq2txt classes to CometAPIEmbed and CometAPISeq2txt, and correct supported_models.mdx. (#10298)
### What problem does this PR solve?

Rename the CometEmbed and CometSeq2txt classes to CometAPIEmbed and
CometAPISeq2txt, and correct supported_models.mdx.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-09-26 10:50:56 +08:00
daea357940 Fix: invalid COMPONENT_EXEC_TIMEOUT (#10278)
### What problem does this PR solve?

Fix invalid COMPONENT_EXEC_TIMEOUT. #10273

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-09-25 14:11:09 +08:00
193d93d820 Refactor: Improve the logic clean conf for ZhipuChat (#10274)
### What problem does this PR solve?
Improve the logic clean conf for ZhipuChat

### Type of change
- [x] Refactoring
2025-09-25 10:28:03 +08:00
a1f848bfe0 Fix:max_tokens must be at least 1, got -950, BadRequestError (#10252)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/10235

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2025-09-24 10:49:34 +08:00
38be53cf31 fix: prevent list index out of range in chat streaming (#10238)
### What problem does this PR solve?
issue:
[Bug]: ERROR: list index out of range #10188
change:
fix a potential list index out of range error in chat response parsing
by adding explicit checks for empty choices.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-09-23 19:59:39 +08:00