32d8e514e1
fix:env AGENT_RECURSION_LIMIT not work ( #453 )
...
* fix:env AGENT_RECURSION_LIMIT not work
* fix:add test
* black tests/unit/config/test_configuration.py
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-22 15:23:21 +08:00
b197b0f4cb
Fix empty tuple agent ( #458 )
...
* feat: add support for 'unknown' message agent in MessageListItem and Message type
* fix: update default agent name from 'unknown' to 'planner' in workflow generator
* fix: remove handling for 'unknown' agent in MessageListItem
* fix: remove 'unknown' agent from Message interface
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-22 15:20:12 +08:00
6d8853b7c7
refine the research prompt ( #460 )
2025-07-22 14:49:04 +08:00
c7edaf3e84
refine the research prompt ( #459 )
2025-07-22 14:13:10 +08:00
4d65d20f01
fix: keep applying quick fix for #446 ( #450 )
...
* fix: the Backend returns 400 error
* fix: keep applying quick fix
* fix the lint error
* fixed .env.example settings
2025-07-20 14:10:46 +08:00
ff67366c5c
fix: the Backend returns 400 error ( #449 )
2025-07-20 11:38:18 +08:00
d34f48819d
feat: polish the mcp-server configure feature ( #447 )
...
* feat: disable the MCP server configuation by default
* Fixed the lint and test errors
* fix the lint error
* feat:update the mcp config documents and tests
* fixed the lint errors
2025-07-19 09:33:32 +08:00
75ad3e0dc6
feat: disable the MCP server configuation by default ( #444 )
...
* feat: disable the MCP server configuation by default
* Fixed the lint and test errors
* fix the lint error
2025-07-19 08:39:42 +08:00
dbb24d7d14
fix: fix the bug introduced by coordinator messages update ( #445 )
2025-07-18 21:36:13 +08:00
933f3bb83a
feat: add CORS setting for the backend application ( #443 )
...
* feat: add CORS setting for the backend application
* fix the formate issue
2025-07-18 18:04:03 +08:00
f17b06f206
fix:planner AttributeError 'list' object has no attribute 'get' ( #436 )
2025-07-18 09:27:15 +08:00
c89b35805d
fix: fix the coordinator's forgetting of its own messages. ( #433 )
2025-07-17 08:36:31 +08:00
b04225b7c8
fix: handle empty agent tuple in streaming workflow ( #427 )
...
Prevents IndexError when agent[0] is accessed on empty tuple,
resolving display issues with Gemini 2.0 Flash model.
Fixes #425
2025-07-16 08:59:11 +08:00
b155e1eca6
refactor: refine the prompt enhancer pipeline ( #426 )
2025-07-15 19:21:59 +08:00
448001f532
refactor: human feedback doesn't need to check enough context ( #423 )
2025-07-15 18:51:41 +08:00
0f118fda92
fix: clean up the builder code ( #417 )
...
* fix: clean up the builder code
* fix:reformat the code
2025-07-15 17:22:50 +08:00
bf3bcee8e3
fix: main build fix for the merge #237 ( #407 )
2025-07-13 09:44:28 +08:00
0c46f8361b
feat: support AzureChatOpenAI under configuring azure_endpoint or AZURE_OPENAI_ENDPOINT ( #237 )
...
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-13 09:27:57 +08:00
0dc6c16c42
fix: repair_json_output cannot process msgs that do not starts with {, [ or ``` ( #384 )
...
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-12 23:29:22 +08:00
3c46201ff0
fix: fix the lint check errors of the main branch ( #403 )
2025-07-12 14:43:25 +08:00
2363b21447
fix: some lint fix using tools ( #98 )
...
* fix: some lint fix using tools
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
* fix: md lint
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
* fix: some lint fix using tools
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
* fix: address comments
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
* fix: tests
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
---------
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-12 13:59:02 +08:00
9f8f060506
feat(llm): Add retry mechanism for LLM API calls ( #400 )
...
* feat(llm): Add retry mechanism for LLM API calls
* feat: configure max_retries for LLM calls via conf.yaml
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-07-12 10:12:07 +08:00
dfd4712d9f
feat: add Domain Control Features for Tavily Search Engine ( #401 )
...
* feat: add Domain Control Features for Tavily Search Engine
* fixed
* chore: update config.md
2025-07-12 08:53:51 +08:00
7ad11bf86c
refactor: simplify style mapping by using upper case only ( #378 )
...
* improve: add abort btn to abort the mcp add request.
* refactor: simplify style mapping by using upper case only
* format: execute uv run black --preview . to format python files.
2025-07-04 08:27:20 +08:00
be893eae2b
feat: integrate VikingDB Knowledge Base into rag retrieving tool ( #381 )
...
Co-authored-by: Henry Li <henry1943@163.com>
2025-07-03 10:06:42 +08:00
f27c96e692
fix: the lint error of llm.py ( #369 )
2025-06-26 10:36:26 +08:00
b7373fbe70
Add support for self-signed certs from model providers ( #276 )
...
* Add support for self-signed certs from model providers
* cleanup
---------
Co-authored-by: tonydoesathing <tmastromarino@cpacket.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2025-06-26 10:17:26 +08:00
dcdd7288ed
test: add unit tests of the app ( #305 )
...
* test: add unit tests in server
* test: add unit tests of app.py in server
* test: reformat the codes
* test: add more tests to cover the exception part
* test: add more tests on the server app part
* fix: don't show the detail exception to the client
* test: try to fix the CI test
* fix: keep the TTS API call without exposure information
* Fixed the unit test errors
* Fixed the lint error
2025-06-18 14:13:05 +08:00
c0b04aaba2
test: add unit tests for graph ( #296 )
...
* test: added unit test of builder
* test: Add unit tests for nodes.py
* test: add more unit tests in test_nodes
* test: try to fix the unit test error on GitHub
* test: reformate the code of test_nodes.py
* Fix the test error of reset the local argument
* Fixed the test error by setup args
* reformat the code
2025-06-18 10:05:02 +08:00
4fb053b6d2
Revert "fix: solves the malformed json output and pydantic validation error p…" ( #325 )
...
This reverts commit a7315b46df
2025-06-14 22:04:03 +08:00
19fa1e97c3
feat: add deep think feature ( #311 )
...
* feat: implement backend logic
* feat: implement api/config endpoint
* rename the symbol
* feat: re-implement configuration at client-side
* feat: add client-side of deep thinking
* fix backend bug
* feat: add reasoning block
* docs: update readme
* fix: translate into English
* fix: change icon to lightbulb
* feat: ignore more bad cases
* feat: adjust thinking layout, and implement auto scrolling
* docs: add comments
---------
Co-authored-by: Henry Li <henry1943@163.com>
2025-06-14 13:12:43 +08:00
a7315b46df
fix: solves the malformed json output and pydantic validation error produced by the 'planner' node by forcing the llm response to strictly comply with the pydantic 'Plan' model ( #322 )
2025-06-14 10:13:30 +08:00
4c2fe2e7f5
test: add more unit tests of tools ( #315 )
...
* test: add more test on test_tts.py
* test: add unit test of search and retriever in tools
* test: remove the main code of search.py
* test: add the travily_search unit test
* reformate the codes
* test: add unit tests of tools
* Added the pytest-asyncio dependency
* added the license header of test_tavily_search_api_wrapper.py
2025-06-12 20:43:32 +08:00
ee1af78767
test: added unit tests for rag ( #298 )
...
* test: added unit tests for rag
* reformate the code
2025-06-11 19:46:08 +08:00
2554e4ba63
test: add unit tests of llms ( #299 )
2025-06-11 19:46:01 +08:00
447e427fd3
refactor: refine teh background check logic ( #306 )
2025-06-11 11:10:02 +08:00
1cd6aa0ece
feat: implement enhance prompt ( #294 )
...
* feat: implement enhance prompt
* add unit test
* fix prompt
* fix: fix eslint and compiling issues
* feat: add border-beam animation
* fix: fix importing issues
---------
Co-authored-by: Henry Li <henry1943@163.com>
2025-06-08 19:41:59 +08:00
8081a14c21
test:unit tests for configuration ( #291 )
...
* test:unit tests for configuration
* test: update the test_configuration.py file
* test: reformate the test codes
2025-06-07 21:51:26 +08:00
c6ed423021
test: add unit tests of crawler ( #292 )
...
* test: add unit tests of crawler
* test: polish the code of crawler unit tests
2025-06-07 21:51:05 +08:00
0e22c373af
feat: support to adjust writing style ( #290 )
...
* feat: implment backend for adjust report style
* feat: add web part
* fix test cases
* fix: fix typing
---------
Co-authored-by: Henry Li <henry1943@163.com>
2025-06-07 20:48:39 +08:00
cda3870add
fix: enable proxy support in aiohttp by adding trust_env=True ( #289 )
2025-06-07 15:30:13 +08:00
b5ec61bb9d
refactor: refine the graph structure ( #283 )
2025-06-05 12:47:17 +08:00
95257800d2
fix: do not return the server side exception to client ( #277 )
2025-06-05 09:23:42 +08:00
45568ca95b
fix:added sanitizing check on the log message ( #272 )
...
* fix:added sanitizing check on the log message
* fix: reformat the codes
2025-06-03 11:50:54 +08:00
db3e74629f
fix: added permissions setting in the workflow ( #273 )
...
* fix: added permissions setting in the workflow
* fix: reformat the code of src/tools/retriever.py
2025-06-03 11:48:51 +08:00
4ddd659d8d
feat: rag retrieving tool call result display ( #263 )
...
* feat: local search tool call result display
* chore: add file copyright
* fix: miss edit plan interrupt feedback
* feat: disable pasting html into input box
2025-05-29 19:52:34 +08:00
56e35c6b7f
feat: support llm env in env file ( #251 )
2025-05-28 16:21:40 +08:00
462752b462
feat: RAG Integration ( #238 )
...
* feat: add rag provider and retriever
* feat: retriever tool
* feat: add retriever tool to the researcher node
* feat: add rag http apis
* feat: new message input supports resource mentions
* feat: new message input component support resource mentions
* refactor: need_web_search to need_search
* chore: RAG integration docs
* chore: change example api host
* fix: user message color in dark mode
* fix: mentions style
* feat: add local_search_tool to researcher prompt
* chore: research prompt
* fix: ragflow page size and reporter with
* docs: ragflow integration and add acknowledgment projects
* chore: format
2025-05-28 14:13:46 +08:00
0565ab6d27
fix: fix unittes & background investigation search logic ( #247 )
2025-05-28 14:05:34 +08:00
29be360954
Update nodes.py ( #242 )
...
SELECTED_SEARCH_ENGINE impossible equal to SearchEngine.ARXIV, should be SearchEngine.ARXIV.value, or use the encapsulated get_web_search_tool
2025-05-27 18:58:14 +08:00
55ce399969
test: add background node unit test ( #198 )
...
* test: add background node unit test
Change-Id: Ia99f5a1687464387dcb01bbee04deaa371c6e490
* test: add background node unit test
Change-Id: I9aabcf02ff04fda40c56f3ea22abe6b8f93bf9b6
* test: fix test error
Change-Id: I3997dc53a2cfaa35501a1fbda5902ee15528124e
* test: fix unit test error
Change-Id: If4c4cd10673e76a30945674c7cda198aeabf28d0
* test: fix unit test error
Change-Id: I3dd7a6179132e5497a30ada443d88de0c47af3d4
2025-05-20 14:25:35 +08:00
8bbcdbe4de
feat: config max_search_results for search engine ( #192 )
...
* feat: implement UI
* feat: config max_search_results for search engine via api
---------
Co-authored-by: Henry Li <henry1943@163.com>
2025-05-18 13:23:52 +08:00
c6bbc595c3
Fix :This PR can resolve the issue of exceeding the default tool invocation limit by setting the recursion limit through an environment variable.mit ( #138 )
...
* set ecursion limit
* set ecursion limit
* fix:check if the recession_limit within a reasonalbe range
* style: format code with black
2025-05-17 20:37:03 -07:00
f7d79b6d83
refactor: upgrade langgraph version ( #148 )
2025-05-18 11:29:41 +08:00
e27c43f005
fix: add model_dump ( #137 )
...
Co-authored-by: Willem Jiang <143703838+willem-bd@users.noreply.github.com>
2025-05-16 21:05:46 +08:00
5cc0e61297
refactor: refine the step execute human message ( #144 )
2025-05-14 18:54:14 +08:00
f73a7a229c
refactor: add existing research findings into step human message ( #140 )
2025-05-14 18:40:14 +08:00
3d5e579ebd
fix: fix start error when search engine is not tavliy and env TAVILY_API_KEY not exist ( #133 )
...
Change-Id: I58e865a11e89acaa3c0b884578cd995d0e9b5422
2025-05-14 14:45:36 +08:00
71808802de
refactor: stess the time range while using web search tools ( #100 )
2025-05-13 18:01:38 +08:00
9266201fe5
fix: background investigator node support more search engine ( #75 )
...
Change-Id: I030a2b9218dfbda2dd2383b7a73266dd7de589c7
2025-05-12 20:15:47 +08:00
97a15dce36
refactor: refactor the prompt management mechanism ( #17 )
2025-05-09 15:50:46 +08:00
091f437bc5
feat: add necessary log when no tool calls ( #16 )
2025-05-09 14:22:07 +08:00
f8b718fcc1
refactor: refactor podcast genration stability ( #11 )
2025-05-09 11:34:19 +08:00
8cb4c3b7cd
chore: add github workflow for lint&ut ( #9 )
2025-05-08 21:47:47 +08:00
daf2e57f14
fix: unify naming
2025-05-08 08:59:18 +08:00
5c96ebe20d
feat: remove `reasoning_llm` and `vl_llm` for now
2025-05-07 17:23:25 +08:00
f30ec77d6f
feat: Add configurable timeout support for MCP server operations with improved defaults
2025-05-01 23:49:49 +08:00
8bdd031c56
feat: emphasis on “directly output”
2025-05-01 15:39:42 +08:00
2473312779
feat: update prompt of researcher
2025-05-01 14:13:35 +08:00
dab1ba4789
fix(planner): skip human feedback if context is sufficient
...
Change-Id: I2b5628a7a8ecb6a6bad2712a9ff81b9b1cd323c6
2025-04-29 18:17:27 +08:00
741e2f0e62
feat: add tiptap table extension
2025-04-28 10:29:35 +08:00
66794a4b73
feat: prose completion api
2025-04-28 10:29:35 +08:00
08de9e0cab
feat: implement basic layout of landing page
2025-04-28 10:07:36 +08:00
899438eca0
feat(nodes): add background investigation node
...
Change-Id: I96e08e22fc7c52647edbf9be4f385a8fae9b449a
2025-04-27 20:15:42 +08:00
ada5e34eeb
feat: add LOCALE variable to agent prompts
2025-04-26 20:57:38 -07:00
72e70357b2
docs: add more suggestions on formatting to enrich the report
2025-04-25 14:13:13 +08:00
3e4e551613
fix: add server name in desc
2025-04-23 18:02:58 +08:00
475dd0f286
feat: refine researcher prompt for mcp
2025-04-23 17:40:08 +08:00
0cf859b393
feat: support mcp settings
2025-04-23 16:00:01 +08:00
dae036f583
feat: implement tools loading api
2025-04-23 14:38:04 +08:00
abdc740531
feat: add langgraph.json for langgraph studio debug
2025-04-22 15:34:06 +08:00
e586f5b31d
feat: use enegertic tts voice type
2025-04-22 12:01:45 +08:00
3d1d289dbd
fix: fix podcast issue
2025-04-22 11:50:59 +08:00
afb8571cbd
feat: use doubao model by default
2025-04-22 11:04:36 +08:00
52313b2405
fix: fix multi-round issue
2025-04-21 20:16:42 +08:00
8129765105
feat: use the same language as report
2025-04-21 19:55:03 +08:00
b67b04ff5d
feat: support multi-language
2025-04-21 19:50:34 +08:00
0d2f93c773
feat: add ppt generation feat
2025-04-21 16:43:06 +08:00
d81eb40a80
feat: put images in the middle of the report
2025-04-21 14:45:52 +08:00
f96873ca02
feat: change speed ratio
2025-04-19 22:34:51 +08:00
4d33aeed6a
feat: pass params from HTTP post body
2025-04-19 22:11:41 +08:00
19d8a59def
fix: use "json_mode"
2025-04-19 22:02:14 +08:00
7497857b71
chore: add copyright
2025-04-19 17:52:23 +08:00
be5f823395
feat: support Podcast generation
2025-04-19 17:37:40 +08:00
6ffe46e39b
feat: support images in the search results
2025-04-19 09:57:02 +08:00
f93a4ab18f
Merge branch 'main' of code.byted.org:langmanus/deer-flow
2025-04-18 15:35:36 +08:00
a6ab97c970
feat: integrate volcengine tts functionality
2025-04-18 15:28:31 +08:00
a56a6f6e0e
feat: enhance the structure of output
2025-04-17 18:01:31 +08:00
27f41b6ad5
feat: Emphasize `title` in structure
2025-04-17 17:46:28 +08:00
b2f14d1737
chore: change project name
2025-04-17 16:17:31 +08:00
道心坚定韩道友
Affan Shaikhsurab
DanielWalnut
Willem Jiang
道心坚定韩道友
Kuro Akuta
Shiwen Cheng
cmq2525
yihong
Kirk Lin
HagonChan
Abeautifulsnow
殷逸维
Tony M
Tax
Xintao Wang
JeffJiang
wushiai1109
laundry
changqingla
Wang Hao
Zhao Longjie
Li Xin
Jiang Feng
He Tao