xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-06-04 21:06:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,612 Commits 36 Branches 198 Tags
7c59bc1ce504bc3cd2efd262a6e5a5ef6aa49aa8
Commit Graph

134 Commits

Author SHA1 Message Date
Dong_master
7c59bc1ce5 feat:add anthropic stream ouput 2025-08-10 00:09:19 +08:00
Dong_master
eede354d3b fix:chatcmpl.py del content <think>,in the ppiochatcmpl.py and modelsopechatcmpl.py fun _closure_stream stream logic 2025-08-09 02:46:13 +08:00
Junyan Qin
261f50b8ec feat: refactor with cursor max mode claude 4.1 opus 2025-08-07 15:47:57 +08:00
Junyan Qin
02dbe80d2f perf: model testing 2025-08-07 10:01:04 +08:00
Dong_master
3a82ae8da5 fix: the bug in the "remove_think" function. 2025-08-06 23:00:57 +08:00
Dong_master
e88302f1b4 fix:The handling logic of remove_think in the connector and Temporarily blocked the processing of streaming tool calls in the runner. 2025-08-05 04:24:03 +08:00
Junyan Qin
7f25d61531 fix: minor fix 2025-08-04 23:00:54 +08:00
Junyan Qin
15e524c6e6 perf: move remove-think to output tab 2025-08-04 19:26:19 +08:00
fdc
4a1d033ee9 fix: Reduce chunk returns in dify and Hundred Refining Runner to every 8 chunks 2025-08-04 19:26:19 +08:00
fdc
8adc88a8c0 fix:Modify the remove_think that directly retrieves the configuration file from the requester, retrieves it from the runner, and passes it to the required function 2025-08-04 19:26:18 +08:00
Dong_master
fcef784180 fix: In the runner, every 8 tokens yield 2025-08-04 19:26:18 +08:00
Junyan Qin
b9f768af25 perf: minor fixes 2025-08-04 19:26:18 +08:00
Junyan Qin
47ff883fc7 perf: ruff format & remove stream params in requester 2025-08-04 19:26:18 +08:00
Dong_master
a9776b7b53 fix:del some print ,and amend respback on stream judge ,and del in dingtalk this is_stream_output_supported() use 2025-08-04 19:26:16 +08:00
Dong_master
0042629bf0 feat:add ppio and openrouter llm stream,and ppio think in content remove_think. 
fix: giteeai stream no remove_think content add char"<think>"
 2025-08-04 19:26:16 +08:00
Dong_master
a7d638cc9a feat:add deepseek and modelscope llm stream,and giteeai think in content remove_think 2025-08-04 19:26:16 +08:00
Dong_master
f84a79bf74 perf:del dify stream in ai.yaml config.and enbale stream in lark.yaml. 
fix:localagent remove_think bug
 2025-08-04 19:26:15 +08:00
Dong_master
f9a5507029 fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及有思考的think处理 
feat:增加带有深度思考模型的think的去think操作
feat:dify中聊天机器人，chatflow对流式的支持
 2025-08-04 19:26:15 +08:00
Dong_master
5ce32d2f04 fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及带有深度思考模型的think增加 2025-08-04 19:26:15 +08:00
Dong_master
4908996cac 流式基本流程已通过修改了yield和return的冲突导致的问题 2025-08-04 19:26:15 +08:00
fdc
b65670cd1a feat: 实现流式消息处理支持 2025-08-04 19:26:14 +08:00
Junyan Qin (Chin)
4a8f5516f6 feat: add new api requester (#1596) 2025-08-03 22:30:52 +08:00
Junyan Qin
0f585fd5ef fix(moonshot): make api.moonshot.ai the default api base url 2025-07-26 22:23:33 +08:00
Junyan Qin
92c3a86356 feat: add qhaigc 2025-07-24 22:42:26 +08:00
Junyan Qin
ebd542f592 feat: 302.AI embeddings 2025-07-24 22:05:15 +08:00
Junyan Qin
194b2d9814 feat: supports more embedding providers 2025-07-24 22:03:20 +08:00
Junyan Qin
7aed5cf1ed feat: ollama embeddings models 2025-07-24 10:36:32 +08:00
Junyan Qin (Chin)
bb672d8f46 Merge branch 'master' into feat/rag 2025-07-18 00:45:24 +08:00
Junyan Qin
2f2db4d445 feat(rag): make embedding and retrieving available 2025-07-16 21:17:18 +08:00
Junyan Qin
f244795e57 fix: rename to '302.AI' 2025-07-16 11:36:57 +08:00
WangCham
b7c57104c4 feat: add embedder 2025-07-13 23:04:03 +08:00
Junyan Qin
0e5c9e19e1 feat: complete support_type for 302ai and compshare requester 2025-07-05 21:03:14 +08:00
devin-ai-integration[bot]
d2b93b3296 feat: add embeddings model management (#1461) 
* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>
 2025-07-05 20:07:15 +08:00
Junyan Qin
3f0153ea4d doc: fix incorrect 302.AI name 2025-07-03 17:26:17 +08:00
Junyan Qin (Chin)
abd02f04af Feat/compshare requester (#1561) 
* feat: add compshare requester

* doc: add compshare to README
 2025-07-03 15:04:02 +08:00
Junyan Qin
89c1972abe perf: skip broken models and bots in bootstrap 2025-06-30 21:29:38 +08:00
Junyan Qin (Chin)
c959c99e45 Feat/302 ai (#1558) 
* feat: add 302.AI requester

* doc: add 302.AI to README
 2025-06-30 21:05:32 +08:00
Junyan Qin
8917050fae chore: add ppio icon 2025-05-31 20:00:18 +08:00
Junyan Qin (Chin)
8ad60b5b64 refactor: gemini requester (#1490) 
* refactor: use openai compatible api for gemini

* chore: remove codes
 2025-05-31 13:11:53 +08:00
aberry
8dfef1d118 Bugfix (#1482) 
* Update modelscopechatcmpl.py

tool_call 流式输出的最后一个参数是 None，需要判断一下

* Update mcp.py

问题：闭包（closure）对循环变量 tool 的捕获，导致最终注册到 self.functions 里的所有 func，都会引用 同一个（最后一个）tool

解决：在定义 func 时，通过函数参数的 默认值 把当下的 tool “冻结”住

* Update mcp.py
 2025-05-27 15:09:09 +08:00
Junyan Qin (Chin)
a7d2a68639 feat: add supports for testing llm models (#1454) 
* feat: add supports for testing llm models

* fix: linter error
 2025-05-19 23:10:04 +08:00
Junyan Qin (Chin)
1992934dce fix: user_funcs typo in ollama chat requester (#1431) 2025-05-15 20:51:58 +08:00
Junyan Qin (Chin)
f376c9703a feat: add supports for open router (#1422) 2025-05-14 21:28:33 +08:00
Junyan Qin
c835555a59 chore: change zh_CN to zh_Hans 2025-05-14 16:44:48 +08:00
Junyan Qin
39f9400de7 fix: modelscope no usable 2025-05-14 15:35:37 +08:00
devin-ai-integration[bot]
ac1d39580b feat: add Google Gemini API support (#1418) 
* feat: add Google Gemini API support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* fix: remove unused imports

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add google-genai dependency

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* fix: update Gemini API implementation to use correct API methods

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: improve Gemini API implementation based on official documentation

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* fix: remove unsupported timeout parameter from Gemini API implementation

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* fix: correct Gemini API implementation based on official documentation

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: update geminichatcmpl

* deps: add google-generativeai

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>
 2025-05-14 15:05:04 +08:00
Junyan Qin (Chin)
015be6008d fix: bugs in requesters (#1401) 2025-05-13 16:09:23 +08:00
Junyan Qin (Chin)
13d36412dd fix: llm model wrongly required when runner is not local-agent (#1386) 2025-05-12 14:16:17 +08:00
Junyan Qin
055b389353 style: restrict line-length 2025-05-10 18:04:58 +08:00
Junyan Qin
b30016ed08 fix: args bugs of chatcmpl 2025-05-10 18:02:05 +08:00