fix: add missing env vars and default values of service_conf.yaml (#9289)
### What problem does this PR solve?
Add missing env var `MYSQL_MAX_PACKET` to service_conf.yaml.template,
and add default values to opendal config to fix npe.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
#9082#6365
<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Bug fix: OpenSearch chunk update some api error (#9032)
### What problem does this PR solve?
Fix a small non-blocking main workflow bug about chunk update When
OpenSearch is the doc engine.
When you wanna enable/disable a chunk in the web-page “Knowledge Base /
Dataset / Chunk”, the bug ocurred.
<img width="2388" height="662" alt="image"
src="https://github.com/user-attachments/assets/575987a0-c929-4589-bfa0-ba54e137cfd9"
/>
The reaseon why it ocurred is that some api params between OpenSearch
and ES differs. It functioned well no matter enable/disable/rewrite the
chunk after I fixed. I also checked the result when using the chat
web-page.
<img width="2394" height="660" alt="image"
src="https://github.com/user-attachments/assets/8b899dc6-d769-4e80-8dd8-ad0fbbca5f78"
/>
I will still focus on vector-database espeically OpenSearch.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: 张雨豪 <zhangyh80@chinatelecom.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
use quote_plus to escape password in opendal's mysql url (#8976)
### What problem does this PR solve?
Use `quote_plus` to escape password in opendal's mysql url to support
special characters like `#`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
when``` if 'signature_version' in self.s3_config:``` and ```if
'addressing_style' in self.s3_config:``` both true.
the config init is error, will be overwrite by last one.
this pr is for fix that case.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
fix opendal config 'oss_table' and 'max_allowed_packet' (#8611)
### What problem does this PR solve?
Fix the config option name of the opendal table name and setting of
'max_allowed_packet'.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: He Wang <wanghechn@qq.com>
### What problem does this PR solve?
Fix: the output log is incorrect
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liang <xiaofeng.liang@landstech.com.cn>
Fix: Database Query Vulnerable to Injection Attacks in rag/utils/opendal_conn.py (#8408)
**Context and Purpose:**
This PR automatically remediates a security vulnerability:
- **Description:** Detected possible formatted SQL query. Use
parameterized queries instead.
- **Rule ID:**
python.lang.security.audit.formatted-sql-query.formatted-sql-query
- **Severity:** HIGH
- **File:** rag/utils/opendal_conn.py
- **Lines Affected:** 98 - 98
This change is necessary to protect the application from potential
security risks associated with this vulnerability.
**Solution Implemented:**
The automated remediation process has applied the necessary changes to
the affected code in `rag/utils/opendal_conn.py` to resolve the
identified issue.
Please review the changes to ensure they are correct and integrate as
expected.
Fix: opendal storage health attribute not found & remove duplicate operator scheme initialization (#8265)
### What problem does this PR solve?
This PR fixes two issues in the OpenDAL storage connector:
1. The `health` method was missing, which prevented health checks on
the storage backend.
3. The initialization of the `opendal.Operator` object included a
redundant scheme parameter, causing unnecessary duplication and
potential confusion.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Background
- The absence of a `health` method made it difficult to verify the
availability and reliability of the storage service.
- Initializing `opendal.Operator` with both `self._scheme` and
unpacked `**self._kwargs` could lead to errors or unexpected behavior
if the scheme was already included in the kwargs.
### What is changed and how it works?
- Adds a `health` method that writes a test file to verify storage
availability.
- Removes the duplicate scheme parameter from the `opendal.Operator`
initialization to ensure clarity and prevent conflicts.
before:
<img width="762" alt="企业微信截图_46be646f-2e99-4e5e-be67-b1483426e77c"
src="https://github.com/user-attachments/assets/acecbb8c-4810-457f-8342-6355148551ba"
/>
<img width="767" alt="image"
src="https://github.com/user-attachments/assets/147cd5a2-dde3-466b-a9c1-d1d4f0819e5d"
/>
after:
<img width="1123" alt="企业微信截图_09d62997-8908-4985-b89f-7a78b5da55ac"
src="https://github.com/user-attachments/assets/97dc88c9-0f4e-4d77-88b3-cd818e8da046"
/>
Fix: unify opendal config key from `schema` to `scheme` (#8232)
### What problem does this PR solve?
This PR resolves the inconsistency in the opendal configuration where
both `schema` and `scheme` were used as keys. The code and
configuration file now consistently use `scheme`, which helps prevent
configuration errors and runtime issues. This change improves code
clarity and maintainability.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Additional context
- Updated both `conf/service_conf.yaml` and
`rag/utils/opendal_conn.py` to use `scheme` instead of `schema`
- No breaking changes to other configuration fields
### What problem does this PR solve?
#8074
Oss support opendal(including mysql)
### 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?
This PR solve the problems metioned in the
pr(https://github.com/infiniflow/ragflow/pull/7140) which is also
submitted by me
### 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):
### Introduction
I fixed the problems when using OpenSearch as the DOC_ENGINE, the
failures of pytest and the wrong API's return.
Mainly about delete chunk, list chunks, update chunk, retrieval chunk.
The pytest comand "cd sdk/python && uv sync --python 3.10 --group test
--frozen && source .venv/bin/activate && cd test/test_http_api &&
DOC_ENGINE=opensearch pytest test_chunk_management_within_dataset -s
--tb=short " is finally successful.
###Others
As some changes between Elasticsearch And Opensearch differ, some pytest
results about OpenSearch are correct and resonable. However, some pytest
params (skipif params) are incompatible. So I changed some pytest params
about skipif.
As a search engine programmer, I will still focus on the usage of vector
databases (especially OpenSearch) for the RAG stuff.
Thanks for your review
Delete Corresponding Minio Bucket When Deleting a Knowledge Base (#7841)
### What problem does this PR solve?
Delete Corresponding Minio Bucket When Deleting a Knowledge Base
[issue #4113 ](https://github.com/infiniflow/ragflow/issues/4113)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
Fix: whole knowledge graph lost after removing any document in the knowledge base (#7151)
### What problem does this PR solve?
When you removed any document in a knowledge base using knowledge graph,
the graph's `removed_kwd` is set to "Y".
However, in the function `graphrag.utils.get_gaph`, `rebuild_graph`
method is passed and directly return `None` while `removed_kwd=Y`,
making residual part of the graph abandoned (but old entity data still
exist in db).
Besides, infinity instance actually pass deleting graph components'
`source_id` when removing document. It may cause wrong graph after
rebuild.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140)
### What problem does this PR solve?
This PR adds the support for latest OpenSearch2.19.1 as the store engine
& search engine option for RAGFlow.
### Main Benefit
1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is
much better than Elasticsearch
2. For search, OpenSearch2.19.1 supports full-text
search、vector_search、hybrid_search those are similar with Elasticsearch
on schema
3. For store, OpenSearch2.19.1 stores text、vector those are quite
simliar with Elasticsearch on schema
### Changes
- Support opensearch_python_connetor. I make a lot of adaptions since
the schema and api/method between ES and Opensearch differs in many
ways(especially the knn_search has a significant gap) :
rag/utils/opensearch_coon.py
- Support static config adaptions by changing:
conf/service_conf.yaml、api/settings.py、rag/settings.py
- Supprt some store&search schema changes between OpenSearch and ES:
conf/os_mapping.json
- Support OpenSearch python sdk : pyproject.toml
- Support docker config for OpenSearch2.19.1 :
docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template
### How to use
- I didn't change the priority that ES as the default doc/search engine.
Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it
will work.
### Others
Our team tested a lot of docs in our environment by using OpenSearch as
the vector database ,it works very well.
All the conifg for OpenSearch is necessary.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Fix: don't modify S3 file name when not using prefix_path (#7152)
### What problem does this PR solve?
Hello, I encountered a problem when trying to use a S3 backend
(seaweedfs) for storage in RAGFlow: when calling
`STORAGE_IMPL.get("bucket", "key")`, the actual request sent to S3 is
`bucket/bucket/key`, causing a `NoSuchKey` error.
I compared the code in `s3_conn.py` to `minio_conn.py` and
`oss_conn.py`, then decided to remove the `else` branch in
`use_prefix_path` method, and it works. I didn't configure `prefix_path`
or `bucket` in `s3` section of the `service_conf.yaml`.
I think this is a bug, but not sure.
### 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):
feat: Recover pending tasks while pod restart. (#7073)
### What problem does this PR solve?
If you deploy Ragflow using Kubernetes, the hostname will change during
a rolling update. This causes the consumer name of the task executor to
change, making it impossible to schedule tasks that were previously in a
pending state.
To address this, I introduced a recovery task that scans these pending
messages and re-publishes them, allowing the tasks to continue being
processed.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---------
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
Fix: knowledge graph resolution with infinity raise error tokenizing in specific situations (#7048)
### What problem does this PR solve?
When running graph resolution with infinity, if single quotation marks
appeared in the entities name that to be delete, an error tokenizing of
sqlglot might occur after calling infinity.
For example:
```
INFINITY delete table ragflow_xxx, filter knowledge_graph_kwd IN ('entity') AND entity_kwd IN ('86 IMAGES FROM PREVIOUS CONTESTS', 'ADAM OPTIMIZATION', 'BACKGROUND'ESTIMATION')
```
may raise error
```
Error tokenizing 'TS', 'ADAM OPTIMIZATION', 'BACKGROUND'ESTIMATION''
```
and make the document parsing failed。
Replace one single quotation mark with double single quotation marks can
let sqlglot tokenize the entity name correctly.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: Handle the case of deleting empty blocks. Update the relevant message (#6643)
…gic to return the correct deletion message. Add handling for empty
arrays to ensure no errors occur during the deletion operation. Update
the test cases to verify the new logic.
### What problem does this PR solve?
fix this bug：https://github.com/infiniflow/ragflow/issues/6607
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Feat: extend S3 storage compatibility and add knowledge base ID prefix (#6355)
### What problem does this PR solve?
- Added support for S3-compatible protocols.
- Enabled the use of knowledge base ID as a file prefix when storing
files in S3.
- Updated docker/README.md to include detailed S3 and OSS configuration
instructions.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix knowledge_graph_kwd on infinity. Close #6476 and #6624 (#6651)
### What problem does this PR solve?
Fix knowledge_graph_kwd on infinity. Close #6476 and #6624
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Prevent applications from failing to start due to calling non-existent
or incorrect Minio connection configurations when using file storage
outside of Minio
### 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?
Removed set_entity and set_relation to avoid accessing doc engine during
graph computation.
Introduced GraphChange to avoid writing unchanged chunks.
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
Call register_scripts on connecting redis
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add vision LLM PDF parser
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Regards kb_id at ElasticSearch insert, update, delete. (#6105)
### What problem does this PR solve?
Regards kb_id at ElasticSearch insert, update, delete. Close #6066
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Kevin Hu
He Wang
Yongteng Lei
Zhichang Yu
pyyuhao
湛露先生
symvation
kira-offgrid
changqingla
cutiechi
africa-worker
Jacky Wu
Hao Zhang
alkscr
Song Fuchang
liuzhenghua
liwenju0
RedBookOfMemory
Zanyatta