Dong_master
|
46fbfbefea
|
fix: in the dashscopeapi.py stream and non-stream remove_think logic
|
2025-08-16 02:13:45 +08:00 |
|
Dong_master
|
8f863cf530
|
fix: remove_think bug
|
2025-08-15 00:55:39 +08:00 |
|
Dong_master
|
2351193c51
|
fix: in the difysvapi.py add stream , and remove_think on chunk
|
2025-08-15 00:50:32 +08:00 |
|
Dong_master
|
8c87a47f5a
|
fix: in the ollamachat.py func _closure add remove_think agr
|
2025-08-14 22:35:30 +08:00 |
|
Dong_master
|
b8b9a37825
|
fix: in the dify non-stream remove_think lgic
|
2025-08-14 22:32:22 +08:00 |
|
Dong_master
|
85f97860c5
|
fix: Fixed the errors in modelscopechatcmpl.py when in pseudo-non-streaming mode, regarding the display of main content and tool calls.
|
2025-08-13 01:55:06 +08:00 |
|
Dong_master
|
8fd21e76f2
|
fix: Only when messagechunk is present, will msg_sequence be assigned to the subsequent tool calls.
|
2025-08-13 00:00:10 +08:00 |
|
Dong_master
|
cc83ddbe21
|
fix: del print
|
2025-08-12 23:29:32 +08:00 |
|
Dong_master
|
99fcde1586
|
fix: in the MessageChunk add msg_sequence ,And obtain the usage in the adapter.
|
2025-08-12 23:20:41 +08:00 |
|
Dong_master
|
4668db716a
|
fix: fix command reply_message error bug,del some print
|
2025-08-12 20:54:47 +08:00 |
|
Dong_master
|
e744e9c4ef
|
fix: in the localagent.py yield MessageChunk add agr tool_calls,and After calling the "tool_calls", the first returned body data will be concatenated.
|
2025-08-12 11:25:37 +08:00 |
|
Dong_master
|
6d35fc408c
|
fix: some time in the anthropicmsgs.py mesg_dcit["content"] is str can not append
|
2025-08-12 11:15:17 +08:00 |
|
Dong_master
|
0607a0fa5c
|
fix: in the modelscopechatcmpl.py stream tool_calls arguments bug,
|
2025-08-12 00:04:21 +08:00 |
|
Dong_master
|
ed57d2fafa
|
del localagent.py print
|
2025-08-11 23:49:19 +08:00 |
|
Dong_master
|
a381069bcc
|
fix:fix tool_result argument bug
|
2025-08-11 23:05:47 +08:00 |
|
Dong_master
|
46452de7b5
|
fix:The handling of the streaming tool calls has been fixed, but there are still bugs in the model's reply messages with thoughtfulness.
|
2025-08-10 23:14:57 +08:00 |
|
Dong_master
|
03b11481ed
|
fix:fix remove_think logic, and end<think> fix </think>
|
2025-08-10 00:28:55 +08:00 |
|
Dong_master
|
8c5cb71812
|
fix:del the chatcmpl.py useless logic,and in the modelscopechatcmpl.py Non-streaming add and del <think> logic,and fix the ppiochatcmpl.py stream logic and the giteeaichatcmpl.py inherit ppiochatcmpl.py
|
2025-08-10 00:16:13 +08:00 |
|
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
|
074d359c8e
|
feat:add dashscopeapi stream
fix:dify 64chunk yield
|
2025-08-04 19:26:16 +08:00 |
|
Dong_master
|
4905b5a738
|
feat:add dingtalk stream
fix:adapter is_stream_output_supported bug
fix:stream message reply chunk in message_id
|
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
|
f5a0cb9175
|
feat:add dify _agent_chat_message streaming
|
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 |
|
zejiewang
|
ba4b5255a2
|
feat:support dify message streaming output (#1437)
* fix:lark adapter listeners init problem
* feat:support dify streaming mode
* feat:remove some log
* fix(bot form): field desc missing
* fix: not compatible with chatflow
---------
Co-authored-by: wangzejie <wangzejie@meicai.cn>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
|
2025-08-04 18:45:52 +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
|
b61bd36b14
|
perf(rag): ui and related apis
|
2025-07-18 00:45:38 +08:00 |
|