Commit Graph

3172 Commits

Author SHA1 Message Date
Aries-ckt
421004a1d8
feat(RAG):add tree retriever based on document directory level (#2669) 2025-05-10 13:02:26 +08:00
Fangyin Cheng
3a00aca113
feat(agent): Optimize agent memory (#2665) 2025-04-30 09:49:17 +08:00
Tam
b901cbc9a6
feat(agent): The SQL execution result of the DataScientist can be passed to the next agent (#2654)
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-04-29 19:28:09 +08:00
Fangyin Cheng
2abd68d6c0
feat(model): Support Qwen3 models (#2664) 2025-04-29 09:55:28 +08:00
Gecko Security
bcb43266cf
[BUG] SQL Injection through CVE Bypass in DB-GPT 0.7.0 (CVE-2024-10835 & CVE-2024-10901) (#2650)
Co-authored-by: nkoorty <amalyshau2002@gmail.com>
Co-authored-by: Fangyin Cheng <staneyffer@gmail.com>
2025-04-28 13:54:41 +08:00
Gecko Security
b16c6793ec
[BUG] RCE Vulnerability in DB-GPT Plugin Upload System (#2649)
Co-authored-by: nkoorty <amalyshau2002@gmail.com>
2025-04-28 13:53:42 +08:00
paxionfruit
445076b433
feat: add model provider InfiniAI (#2653)
Co-authored-by: yaozhuyu <yaozhuyu@infini-ai.com>
2025-04-27 16:22:31 +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
Cooper
0b3ac35ede
fix(model): fix remote reranker api & fix long_term memory (#2648)
Co-authored-by: dong <dongzhancai@iie2.com>
2025-04-24 11:17:20 +08:00
magic.chen
e78d5370ac
fix(agent): Fix long-term memory error (#2644)
# Description

Closes #2642
Closes #2637

# How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration

# 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
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] Any dependent changes have been merged and published in downstream
modules
2025-04-23 13:49:55 +08:00
Fangyin Cheng
a059ef1412 fix(agent): Fix long-term memory error 2025-04-23 11:09:59 +08:00
Fangyin Cheng
3d7d52250f
feat(model): Proxy multimodal supports (#2641) 2025-04-21 19:36:29 +08:00
magic.chen
a6680610b9
fix(reranker) The rerank model is used during the knowledge base recall for chat scenarios and recall test scenarios (#2638)
fix https://github.com/eosphoros-ai/DB-GPT/issues/2636 

# Description

Currently, the reranker model is not used for knowledge base recalls, In
the recall test function, the CFG.RERANK_MODEL is always none
In chat scenarios, knowledge base recalls are also not rerankered


# How Has This Been Tested?


![image](https://github.com/user-attachments/assets/179a6371-98bb-441e-9c13-1215bfd73374)

![image](https://github.com/user-attachments/assets/572f4c25-0a2b-4bcf-a11c-28c146a290b1)


# 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
2025-04-21 11:13:03 +08:00
tam
32b1fd4c1e feat(knowledge): add reranking functionality for simple_assistant_agent and summary_assis_agent
- Implement reranking of retrieved chunks when needed
- Improve relevance of search results by ranking chunks based on query
2025-04-21 09:58:01 +08:00
tam
b0ef14c111 fmt(knowledge): reformat retriever resource code
- Adjust import order for better organization
- Improve code readability with proper line breaks and indentation
- Remove unnecessary empty lines
2025-04-19 17:48:54 +08:00
tam
fbfc972908 feat(knowledge): integrate reranking functionality into RetrieverResource
- Add reranking support to improve the quality of retrieved chunks
- Implement RerankEmbeddingFactory and RerankEmbeddingsRanker
- Update RetrieverResource to use reranking when configured
- Modify retrieve method to apply reranking if needed
2025-04-19 17:38:09 +08:00
tam
cc287702bc fix(reranker)In the recall test scenario, the reranking logic is updated based on the application configuration
The logic for determining whether to use reranking and setting the `top_k` value now depends on the `app_config` instead of directly using `CFG.RERANK_MODEL` and `CFG.RERANK_TOP_K`. This change ensures that the application's specific configuration settings are respected.
2025-04-19 15:20:10 +08:00
dobet
129509fcd2
fix connect mssql embedding error (#2589) 2025-04-17 12:44:51 +08:00
magic.chen
8d66d0271f
fix:storage add collection bug (#2615)
Close #2595 
# Description
fix hybrid memory milvus create collection bug 

# How Has This Been Tested?

switch milvus for hybrid storage type.

# Snapshots:

Include snapshots for easier review.

# Checklist:

- [ ] My code follows the style guidelines of this project
- [ ] I have already rebased the commits and make the commit message
conform to the project standard.
- [ ] 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
2025-04-15 22:48:26 +08:00
Fangyin Cheng
17b7e5ba0c
feat(model): Support GLM-4-0414 (#2630) 2025-04-15 22:48:18 +08:00
alanchen
7de6937865
fix(docs): update doc example code to work (#2624)
Co-authored-by: alan.cl <alan.cl@antgroup.com>
2025-04-15 22:45:55 +08:00
Fangyin Cheng
5e7f3568d3
feat(model): Multimodal supports (#2627) 2025-04-15 16:29:02 +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
magic.chen
0245cfdff8
fix(storage): Fix load too many chunks error (#2614)
# Description

Closes #2607

# How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration

# 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
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] Any dependent changes have been merged and published in downstream
modules
2025-04-12 20:48:59 +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
ethan
61565f7369
fix: the issue is the app_code can't be stored in the chat_history… (#2606)
Co-authored-by: 9527 <9527@163.com>
2025-04-11 16:41:04 +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
Tam
ae4112cf35
fix(schema): change flow_data column type from text to longtext (#2590)
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-04-09 12:36:19 +08:00
Fangyin Cheng
e9ce534ca1
feat(agent): Support SSL/TLS for MCP (#2591) 2025-04-08 08:47:41 +08:00
Cooper
0fd578cf87
fix(agents): fix ReActAgent (#2588) 2025-04-07 13:04:55 +08:00
Fangyin Cheng
3ceba89102
feat(build): Add git for docker image (#2584) 2025-04-03 10:47:03 +08:00
alanchen
5dbfb24a86
Fix ChatWithDbQA param validate (#2569)
Co-authored-by: alan.cl <alan.cl@antgroup.com>
2025-04-03 09:49:48 +08:00
magic.chen
e7b23f6425
feat(agent): Support MCP authentication (#2582)
# Description

Support MCP authentication(SSE).

# How Has This Been Tested?

```python
from dbgpt.agent.resource import  MCPToolPack

tools = MCPToolPack(
    "http://127.0.0.1:8000/sse"
    default_headers={"Authorization": "Bearer your_token"}
)
# Set the default headers for each server
tools2 = MCPToolPack(
    "http://127.0.0.1:8000/sse"
    headers = {
        "http://127.0.0.1:8000/sse": {
            "Authorization": "Bearer your_token"
        }
    }
)

```

# Snapshots:

Website:


![image](https://github.com/user-attachments/assets/f7f96fa5-dd21-4a81-86f3-2a73a3fc464f)



# 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
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] Any dependent changes have been merged and published in downstream
modules
2025-04-03 09:47:19 +08:00
Fangyin Cheng
2e0e140b51 feat(agent): Support MCP authentication 2025-04-03 09:21:05 +08:00
yyhhyy
0b6633703d
fix(web): Fix resource binding bug (#2572) 2025-04-02 20:19:44 +08:00
Fangyin Cheng
59e34e2d89
feat(agent): Compatible with MCP and tools (#2566)
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-04-01 16:03:52 +08:00
Tam
9719c0abcd
fix(knowledge):Fix KB document questions list check logic (#2565)
Co-authored-by: tam <tanwe@fulan.com.cn>
2025-03-31 20:12:45 +08:00
yyhhyy
9fce5cec3d
fix(web): Prevent dragging node when selecting text in parameter input fields (#2560) 2025-03-31 19:55:16 +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
Fangyin Cheng
3bfbdc3fc7
feat(agent): More general ReAct Agent (#2556) 2025-03-31 09:38:31 +08:00
magic.chen
0bdff7a0f2
fix: fix vllm tokenizer count error (#2555)
Co-authored-by: Fangyin Cheng <staneyffer@gmail.com>
2025-03-31 08:31:04 +08:00
magic.chen
c68332be4c
fix: some typos using typos (#2552)
# Description

Please include a summary of the change and which issue is fixed. Please
also include relevant motivation and context. List any dependencies that
are required for this change.

This path fix some of typos using typos just an example

using tools https://github.com/crate-ci/typos

# How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration

# Snapshots:

Include snapshots for easier review.

# Checklist:

- [ ] My code follows the style guidelines of this project
- [ ] I have already rebased the commits and make the commit message
conform to the project standard.
- [ ] 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
2025-03-29 16:39:46 +08:00