Dmitry
845432fea0
feat(model): AI/ML API integration ( #2844 )
2025-07-15 13:17:14 +08:00
stevenlx96
8c14f1981a
fix(core): Update Milvus truncate method for GraphRAG ( #2847 )
2025-07-15 13:15:50 +08:00
Aries-ckt
441cb55377
doc: fix ob rag doc ( #2840 )
2025-07-14 17:18:10 +08:00
Tam
0ecfeabd8e
feat(datasouce): Add GaussDB data source connector ( #2813 )
...
Co-authored-by: tanwei <tanwei@fulan.com.cn>
2025-07-09 22:50:22 +08:00
HYP-hu
cecac56a26
fix: Fix milvus vector_name_exists bug ( #2818 )
2025-07-07 22:52:02 +08:00
jiao-duan
00af86d89e
fix: Fix SummaryExtractor not found error ( #2805 )
2025-07-02 21:43:42 +08:00
geebytes
4cdbb22cb6
fix(core):Remove SQL comments before formatting the SQL ( #2769 )
2025-06-23 14:06:00 +08:00
Aries-ckt
cc81e7af09
chore: tag v0.7.2 ( #2771 )
2025-06-13 17:24:12 +08:00
alanchen
4afa2b84b9
chore: Update dependency reference path ( #2745 )
2025-06-03 11:31:19 +08:00
Aries-ckt
7e9885574a
feat(ChatKnowledge):add hybrid search for knowledge space. ( #2722 )
2025-05-23 18:54:22 +08:00
alanchen
320228ae37
fix: fix unit test and some code typos ( #2717 )
2025-05-23 17:47:00 +08:00
alanchen
d83704d233
fix(VectorStore): fix task concurrency and batch processing issue ( #2671 )
...
- Refactor task execution to improve concurrency control
- Implement batch processing for vector deletion in Chroma store
# Description
1 ,When chunk a knowledge base file, if there are too many chunks ,
using asyncio.gather(*tasks) will cause the CPU to freeze
2 , When using the Chroma vector database, if the one-time deletion of
embedding documents ids exceeds 5461, it will fail

# How Has This Been Tested?
# Snapshots:


Include snapshots for easier review.
# Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have already rebased the commits and make the commit message
conform to the project standard.
- [x] I have performed a self-review of my own code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [ ] Any dependent changes have been merged and published in downstream
modules
2025-05-12 16:25:06 +08:00
Tam
3a65e1b65f
fix(VectorStore) fix MilvusStore to use serialize function for metadata json encoding ( #2672 )
...
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-05-10 13:10:26 +08:00
Aries-ckt
421004a1d8
feat(RAG):add tree retriever based on document directory level ( #2669 )
2025-05-10 13:02:26 +08:00
tam
fc6c9071ff
format code
2025-05-06 23:47:06 +08:00
tam
4eb06299e8
fix(VectorStore): fix task concurrency and batch processing
...
- Refactor task execution to improve concurrency control
- Implement batch processing for vector deletion in Chroma store
2025-05-06 23:23:40 +08:00
luowenwu
1b77ed6319
feat(datasource):add oracle datasource ( #2629 )
...
Co-authored-by: luobin <luobin@wondersgroup.com>
Co-authored-by: Fangyin Cheng <staneyffer@gmail.com>
2025-04-27 16:21:11 +08:00
seoibiubiu
430235bd1b
Fix Clickhouse SQL syntax error for RdbmsSummary ( #2651 )
2025-04-24 22:44:46 +08:00
Fangyin Cheng
3d7d52250f
feat(model): Proxy multimodal supports ( #2641 )
2025-04-21 19:36:29 +08:00
dobet
129509fcd2
fix connect mssql embedding error ( #2589 )
2025-04-17 12:44:51 +08:00
aries_ckt
ac72bb0927
Merge remote-tracking branch 'main-com/main' into fix_issue2590
2025-04-15 10:06:36 +08:00
aries_ckt
2991c7e437
fix:memory create collection bug
2025-04-14 21:29:41 +08:00
aries_ckt
4c6386ad3f
fix:add create collection method for other vector db.
2025-04-13 12:24:16 +08:00
aries_ckt
2fad7485fc
chore:fmt
2025-04-12 14:34:19 +08:00
aries_ckt
5d67f166d9
fix:storage add collection
2025-04-12 14:18:12 +08:00
Fangyin Cheng
c04e3c7cb0
fix(storage): Fix load big documents error
2025-04-11 20:46:48 +08:00
ethan
12170e2504
feat(mode) : Adding the siliconflow embeding proxy ( #2603 )
...
Co-authored-by: 9527 <9527@163.com>
Co-authored-by: Fangyin Cheng <staneyffer@gmail.com>
2025-04-11 16:41:51 +08:00
Fangyin Cheng
5ddd9e5bf8
fix(model): Fix apiserver error ( #2605 )
2025-04-10 10:23:49 +08:00
Tam
babc484261
Fix postgresql ( #2601 )
...
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-04-10 09:40:45 +08:00
geebytes
90e22ac136
fix: Bugfix/elasticsearch store read config dict ( #2577 )
2025-04-10 07:36:43 +08:00
yihong
beafca5c6c
fix: make tugraph work again ( #2551 )
...
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-31 19:46:44 +08:00
geebytes
c86243aa62
feat(KnowledgeBase):Add Word97-2003 (.doc) Binary File parsing module ( #2544 )
2025-03-29 11:05:06 +08:00
aries_ckt
4f2903a6b7
chore:fmt
2025-03-23 19:31:49 +08:00
aries_ckt
d095091525
fix:rag workflow error fix
2025-03-23 19:17:43 +08:00
aries_ckt
eccbe2ba94
Merge remote-tracking branch 'main-com/main' into issue2484
2025-03-23 16:20:50 +08:00
aries_ckt
2107f472e1
fix:rag workflow update
2025-03-23 16:20:40 +08:00
magic.chen
bc6983ddb9
fix: milvus collection search param ( #2481 )
...
line 564:
param = self.index_params_map[index_type].get("params") should remove
get("params");
# Description
查询 milvus 的时候,逻辑是:_search 方法的 param 参数为 None 时,会读取 index_params_map
对应索引的配置参数。但是不应再调用 get("params"),会导致传递给 milvus 的 search
参数是错误的格式,使得参数无效,milvus 会以它自己的默认参数查询。可以参考 milvus
官网:https://milvus.io/api-reference/pymilvus/v2.5.x/MilvusClient/Vector/search.md
# Snapshots:
<img width="999" alt="image"
src="https://github.com/user-attachments/assets/cd44304c-81f2-4073-81b9-c68d066657bb "
/>
<img width="768" alt="image"
src="https://github.com/user-attachments/assets/f2249186-b04b-454b-97f7-b67f958515a1 "
/>
2025-03-21 23:05:35 +08:00
TenYearOldJAVA
3ce3be65b6
fix: doris_conn cannot get table comment to store vectordb ( #2490 )
...
Co-authored-by: Zhihe.Liu <zhihe.liu@majorbio.com>
2025-03-21 10:54:02 +08:00
Fangyin Cheng
52e41bccc9
ci(SDK): Add 0.7.0 workflow ( #2493 )
2025-03-20 15:27:44 +08:00
aries_ckt
2d489bfe45
fix:issue2484
2025-03-19 15:46:40 +08:00
aries_ckt
43763945a8
fix:issue2484
2025-03-18 18:58:43 +08:00
QIN CHONG
463d27b78f
Update milvus_store.py
...
line 564: param = self.index_params_map[index_type].get("params")
2025-03-17 20:49:02 +08:00
Fangyin Cheng
82392dc4eb
fix: Fix chroma check exists bug
2025-03-17 15:57:46 +08:00
Fangyin Cheng
9f2e747698
fix: Fix retrieve error
2025-03-17 15:38:31 +08:00
Fangyin Cheng
b2dd66dc6d
feat(storage): Support oss and s3
2025-03-17 15:38:31 +08:00
Aries-ckt
0d48f37ed9
deps(tongyi): fix tongyi dependencies and add tongyi proxy config ( #2467 )
...
# Description
deps(tongyi): fix tongyi dependencies and add tongyi proxy config
# How Has This Been Tested?
```bash
uv sync --all-packages --frozen --extra "base" --extra "proxy_tongyi" --extra "rag" --extra "storage_chromadb" --extra "dbgpts"
```
```bash
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config .\configs\dbgpt-proxy-tongyi.toml
```
2025-03-17 15:17:12 +08:00
Aries-ckt
fc3fe6b725
refactor: rag storage refactor ( #2434 )
2025-03-17 14:15:21 +08:00
yyhhyyyyyy
b25f6920d1
deps(tongyi): fix tongyi dependencies and add tongyi proxy config
2025-03-14 16:48:29 +08:00
Tam
6a79c8c622
fix (vector store) Database refresh error, vector collection deduplication consistency issue ( #2465 )
...
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-03-14 14:43:44 +08:00
tam
c68f627fe6
fix(datasource): Correct the import path for StarRocks dialect
2025-03-13 12:03:30 +08:00