mginfn
ffe766f24d
chore: added base_url parameter to CochereReranking ( #743 )
...
Co-authored-by: Mauro Gattari <mauro.gattari@infn.it>
2025-06-05 16:35:00 +07:00
TommasoMoroHtx
833982ac81
fix(docstore): preserve retrieval ranking order in lancedb get() ( #745 )
2025-06-05 16:08:49 +07:00
Pang Chun Lam
ddb5187293
fix: scope is not passd to vector store query ( #747 )
2025-06-05 16:08:40 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
5132288386
feat: add VoyageAI's rerank and embeddings models ( #733 ) #none
...
* Introducing VoyageAI's rerank and embeddings models
* fix: comfort CI
* fix: update test case
---------
Co-authored-by: fzowl <zoltan@voyageai.com>
2025-04-15 15:54:23 +07:00
Amin
c33bedca9e
feat: add options for Mistral AI ( #707 ) #none
...
* add Mistral AI emb AI embedding vendor, types
* add mistral env setting to example
* add mistral LLM option
* chore: fix default embedding back to normal
* fix: comfort CI
---------
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2025-04-15 15:11:22 +07:00
Ben Dykstra
9b05693e4f
feat: add structured output to openai ( #603 ) #none
...
* add structured output to openai
* remove notebook, modify prepare output method
* fix: comfort precommit
---------
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2025-04-15 14:54:23 +07:00
Christopher Kao
6f4acc979c
fix: update Docling call to generate figure caption #729 #none
2025-04-15 14:37:36 +07:00
Tadashi
54abe1a535
ci: disable fly deployment #none
2025-04-15 08:28:52 +07:00
Tadashi
a3e2e20735
fix: comfort CI
2025-04-01 11:33:48 +07:00
Benno Löffler
911b20caf0
fix: error 'history_messages' with LightRAG latest version ( #719 ) bump:patch
...
* fix: Error: 'history_messages' with LightRAG
* added comment
2025-04-01 11:31:44 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
2ffe374c2f
feat: add index batch size setting for lightrag ( #720 ) #none
2025-04-01 11:31:06 +07:00
Tzzed
79a5f064a2
fix: rename nonexistent function call in update_macos.sh script ( #687 ) #none
2025-04-01 11:28:30 +07:00
taprosoft
edec6142bf
fix: add pylance req for local script-based install bump:patch
2025-03-31 15:05:31 +00:00
taprosoft
fbc2cd4ce5
fix: add matplotlib req for Colab install bump:patch
2025-03-31 14:53:01 +00:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
86b3ee8b29
fix: update Dockerfile ( #718 ) #none
2025-03-31 13:57:40 +07:00
Tadashi
8f87ddfb31
fix: update default params in sso mode #none
2025-02-14 21:40:23 +07:00
Tadashi
c51c1fce77
fix: windows encoding python bump:patch
2025-02-14 21:36:55 +07:00
Varun Sharma
952026da6c
fix: ValueError breaks Ui #629 ( #630 ) #none
2025-02-14 21:33:35 +07:00
Jinke
8b04f8475a
fix: encoding error after brand new installation ( #654 ) #none
...
fix: encoding error after brand new installation
2025-02-14 21:32:39 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
647d0a4afe
fix: support authentication with Open ID using Keycloak ( #669 ) #none
...
* Changes for authentication with Open ID using Keycloak
* Select authentication method
* fix: missing params
* fix: minor update
---------
Co-authored-by: Sara <sara.jimenez@nuvu.cc>
2025-02-14 21:26:37 +07:00
Varun Sharma
e3921f7704
fix: selecting search all does not work on LightRAG / NanoGraphRAG ( #627 ) #none
...
* fix: base path
* fix: select all doesn't work
* fix: adding new documents should update the existing index within the file collection instead of creating new one #561
* fix linter issues
* feat: update NanoGraphRAG with global collection search
---------
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2025-02-14 21:13:39 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
0b090896fd
feat: add support for reasoning llm with thought visualization ( #652 ) bump:patch
...
* fix: lanceDB query with empty file_ids
* feat: add thinking display
* feat: add low request mode for local llm
2025-02-05 13:45:12 +07:00
Hideyuki Kagami
f5b2200ffa
fix: update parameter name in AzureAIDocumentIntelligenceLoader ( #593 ) bump:patch
2025-02-03 08:10:10 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
756f46893f
fix: lightrag settings ( #649 ) #none
...
* Update lightrag_pipelines.py
* Update nano_pipelines.py
* fix: lightrag setting prompts
---------
Co-authored-by: RoadToNowhereX <37441177+RoadToNowhereX@users.noreply.github.com>
2025-02-03 08:07:53 +07:00
Tadashi
276bf56225
fix: docker CI parallel build
2025-02-02 19:03:12 +07:00
Tadashi
3b87945ab0
fix: plotly requirements #none
2025-02-02 18:58:37 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
3bd3830b8d
feat: sso login, demo mode & new mindmap support ( #644 ) bump:minor
...
* fix: update .env.example
* feat: add SSO login
* fix: update flowsetting
* fix: add requirement
* fix: refine UI
* fix: update group id-based operation
* fix: improve citation logics
* fix: UI enhancement
* fix: user_id to string in models
* fix: improve chat suggestion UI and flow
* fix: improve group id handling
* fix: improve chat suggestion
* fix: secure download for single file
* fix: file limiting in docstore
* fix: improve chat suggestion logics & language conform
* feat: add markmap and select text to highlight function
* fix: update Dockerfile
* fix: user id auto generate
* fix: default user id
* feat: add demo mode
* fix: update flowsetting
* fix: revise default params for demo
* feat: sso_app alternative
* feat: sso login demo
* feat: demo specific customization
* feat: add login using API key
* fix: disable key-based login
* fix: optimize duplicate upload
* fix: gradio routing
* fix: disable arm build for demo
* fix: revise full-text search js logic
* feat: add rate limit
* fix: update Dockerfile with new launch script
* fix: update Dockerfile
* fix: update Dockerignore
* fix: update ratelimit logic
* fix: user_id in user management page
* fix: rename conv logic
* feat: update demo hint
* fix: minor fix
* fix: highlight on long PDF load
* feat: add HF paper list
* fix: update HF papers load logic
* feat: fly config
* fix: update fly config
* fix: update paper list pull api
* fix: minor update root routing
* fix: minor update root routing
* fix: simplify login flow & paper list UI
* feat: add paper recommendation
* fix: update Dockerfile
* fix: update Dockerfile
* fix: update default model
* feat: add long context Ollama through LCOllama
* feat: espose Gradio share to env
* fix: revert customized changes
* fix: list group at app load
* fix: relocate share conv button
* fix: update launch script
* fix: update Docker CI
* feat: add Ollama model selection at first setup
* docs: update README
2025-02-02 15:19:48 +07:00
Tadashi
3006402d7e
docs: update README #none
2025-01-22 15:21:55 +07:00
Tadashi
1f9b52cab2
docs: update README #none
2025-01-22 12:58:40 +07:00
Tadashi
06d3bd4386
docs: update README #none
2025-01-21 10:50:33 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
1c5849c711
docs: improve installation instructions ( #620 ) #none
...
* docs: update instructions
* fix: typo in CONTRIBUTING.md (#614 )
* fix: typo in usage.md (#598 )
minor typo fix (tt -> it)
---------
Co-authored-by: Varun Sharma <contactvarun27@gmail.com>
Co-authored-by: natowi <natowi@users.noreply.github.com>
2025-01-13 07:42:47 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
5343d0d3ee
fix: openai async ( #585 ) bump:patch
2024-12-24 09:45:15 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
95191f53d9
feat: add web search ( #580 ) bump:patch
...
* feat: add web search
* feat: update requirements
2024-12-23 09:28:24 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
4fe080737a
fix: improve citation logic ( #578 ) bump:patch
2024-12-18 20:27:53 +07:00
Tadashi
3bd19f399f
fix: tei_fast_rerank logic bump:patch
2024-12-17 17:33:47 +07:00
Elias Judin
54320d08df
feat(loader): implement markdown parsing in MathpixPDFReader ( #498 )
...
* ✨ feat(loader): implement markdown parsing in MathpixPDFReader
Add functionality to properly handle PDF content:
- Add parse_markdown_text_to_tables method to separate tables and text
- Fix load_data implementation to properly process documents
- Fix lazy_load_data method
- Improve document metadata handling for tables and text sections
The loader now correctly processes PDFs through Mathpix API and converts content to proper Document objects.
* fix(loader): remove super() calls blocking MathpixPDFReader implementation
Remove early returns using super() in load_data and lazy_load_data methods that were preventing the actual implementation from being executed. This fixes the "not implemented" error while maintaining the full PDF reader functionality.
2024-12-17 17:30:17 +07:00
Emmanuel Ferdman
b1e9f98c5a
fix: update flowsettings.py reference ( #506 )
...
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2024-12-17 17:24:33 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
cd87a7e35f
fix: UI tab name and reranking process for TeiFastReranking ( #576 )
...
* fix: update user-management.md
* fix: reranking process when TeiFastReranking is specified.
---------
Co-authored-by: Ryuichi Takano <45957617+tknrych@users.noreply.github.com>
Co-authored-by: Ryuichi Takano <ryuichi.takano@jp.ricoh.com>
2024-12-17 17:23:54 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
9039b4f32b
fix: using a base path breaks file preview ( #575 )
...
* fix: using a base path breaks file preview
* fix: comfort precommit
---------
Co-authored-by: Varun Sharma <contactvarun27@gmail.com>
2024-12-17 17:12:27 +07:00
eddprogrammer
a8b8fcea32
fix: add retry to lightrag llm_func call ( #572 )
...
* add retry to lightrag llm_func call
* fix: update logic for nanographrag
---------
Co-authored-by: Song Lin <song.lin@kirkland.com>
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2024-12-17 17:02:06 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
1d3c4f4433
feat: add graphrag modes ( #574 ) #none
...
* feat: add support for retrieval modes in LightRAG & NanoGraphRAG
* feat: expose custom prompts in LightRAG & NanoGraphRAG
* fix: optimize setting UI
* fix: update non local mode in LightRAG
* fix: update graphRAG mode
2024-12-17 16:49:37 +07:00
Tadashi
c667bf9d0a
fix: update Dockerfile
2024-12-16 08:41:12 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
7a02cb72af
feat: add URL indexing directly from chat input ( #571 ) bump:patch
...
* feat: enable lightrag by default and add graphrag key check
* feat: add URL indexing from chatbox
2024-12-15 23:13:52 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
a0c9a6e8de
feat: add quick setting for follow up chat suggestions & add more common languages ( #556 ) bump:patch
...
* feat: add chat suggestion quick setting
* feat: add more common languages
* fix: minor fixes
2024-12-07 09:19:21 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
6650b15c64
feat: add citation style quick setting ( #554 ) bump:patch
2024-12-05 19:55:59 +07:00
ian
7d8f40e841
docs: add bibtex ( #551 ) #none
2024-12-05 15:13:16 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
b016a84b97
feat: add Google embedding support & update setup ( #550 ) bump:patch
2024-12-04 11:09:57 +07:00
Pedro Lima
159f4da7c9
fix: Remove Collections from all index names ( #473 )
...
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2024-12-04 09:40:46 +07:00
Tran Huu Hoang
32732c35de
feat: set user being able to set chunk size and overlap for indices ( #524 )
...
* use tzlocal to get the local time
* delete tmp folder
* update date_created and date_updated with current timezone
* pass precommit
* update date_created field default by local time
* add chunk size and chunk overlap param for indices
* refactor code to pass pre-commit
* fix: minor update logics
---------
Co-authored-by: Tadashi <tadashi@cinnamon.is>
2024-12-04 09:04:50 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
a1fecfac45
feat: add toggle for conversation control sidebar ( #546 ) #none
2024-12-04 07:53:28 +07:00
