### 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)
### 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>
### What problem does this PR solve?
- Admin service support SHOW SERVICE <id>.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
issue: #10241
### 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)
### What problem does this PR solve?
- Admin client support drop user.
Issue: #10241
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
issue：#5617
change：add IBM DB2 support in ExeSQL
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### 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)
### What problem does this PR solve?
Refactor import modules.
### Type of change
- [x] Refactoring
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Added "怎么办" to the regex pattern in rmWWW method to improve query
cleaning by removing this common question phrase along with other
question words.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### 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)
### 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)
### What problem does this PR solve?
Revert back to chat.completions.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [x] Other (please describe):
Revert back to chat.completions.
### What problem does this PR solve?
Currently, Azure OpenAI returns one minute Quota limit responses when
chat API is utilized. This change is needed in order to be able to
process almost any documents using models deployed in Azure Foundry.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix broken imports
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix: resolve hash collisions by switching to UUID &correct logic for
always-true statements, solved: #10165
Feat: Update GPT api integration, solved: #10204
Feat: Support qianwen-deepresearch, solved: #10163
### 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?
Add tree_merge for law parsers, significantly outperforming
hierarchical_merge, solved: #8637
1. Add tree_merge for law parsers, include build_tree and get_tree by
dfs.
2. add Copyright statement for helath_utils
### Type of change
- [x] Documentation Update
- [x] Performance Improvement
### What problem does this PR solve?
Skip `tag_query` step if `tag_kbs` are empty.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
issue:
[Bug]: anthropic model have not baseurl selecting,need add #8546
change:
This PR adds support for using Anthropic models through a third-party
API by allowing a custom base_url.
It ensures compatibility with both the official Anthropic endpoint and
external providers.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix the rerank_model condition logic by correcting the np.isclose check.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Migrate OpenAI-compatible chats to LiteLLM.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Related PR:
Feat: add CometAPI to LLMFactory and update related mappings #10119
Change:
Fixes the issue where the embedding model in CometAPI was not being
called correctly
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: TensorNull <tensor.null@gmail.com>
### Related issues
#10078
### What problem does this PR solve?
Integrate CometAPI provider.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Support image recognition with image links in markdown files, solved
issue: #8755
Fixed log info error in code_exec, solved issue: #10064
### Type of change (8755)
- [x] New Feature (non-breaking change which adds functionality)
### Type of change (10064)
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Dataflow support audio. And fix giteeAI's sequence2text model.
### 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 parse image by OCR or VLM.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix text input exceed token num limit when using siliconflow's embedding
model BAAI/bge-large-zh-v1.5 and BAAI/bge-large-en-v1.5, truncate before
input.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/9966
### 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?
Dataflow supports markdown.
### 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?
Dataflow supports Spreadsheet and Word processor document
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add LongCat-Flash-Chat from Meituan, deepseek v3.1 from SiliconFlow,
kimi-k2-09-05-preview and kimi-k2-turbo-preview from Moonshot.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The total token was incorrectly accumulated when using the
OpenAI-API-Compatible api.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refine dataflow and initialize dataflow app.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Moved `signature_version` and `addressing_style` parameters to a
`Config` object from `botocore.config`
`signature_version` is now passed as `Config(signature_version='v4')`
`addressing_style` is now passed as `Config(s3={'addressing_style':
'path'})`
The `Config` object is then passed to `boto3.client()` via the `config`
parameter
## Changes Made
- Modified `rag/utils/s3_conn.py` in the `__open__()` method
- Updated parameter handling logic to use `config_kwargs` dictionary
- Maintained backward compatibility for configurations without these
parameters
## Related Issue
Fixes#9910
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Syed Shahmeer Ali <ashahmeer73@gmail.com>
### What problem does this PR solve?
This PR fixes a critical bug in the knowledge base isolation feature
where chat responses were referencing documents from incorrect knowledge
bases. The issue was in the `infinity_conn.py` file where the
`equivalent_condition_to_str()` function was incorrectly skipping
`kb_id` filtering, causing documents from unintended knowledge bases to
be included in search results.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Syed Shahmeer Ali <ashahmeer73@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Add exponential back-off for Chat LiteLLM. #9858.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The default value for OpenAI '/v1/embeddings' parameter
'encoding_format' is 'base64'. Use 'float' explicitly to avoid base64
encoding & decoding, larger data size.
https://github.com/openai/openai-python/blob/main/src/openai/resources/embeddings.py
if not is_given(encoding_format):
params["encoding_format"] = "base64"
### Type of change
- [x] Performance Improvement
