RAGFlow-0.13.0

Summary

• Added team support
• Upgrade UI for Agent
• Added HTTP API for knowledge base, document parsing, dialogs, etc. Python SDK is also provided, which can be installed via pip install ragflow-sdk==0.13.0.
• Added smart chunking for Markdown
• Added context retrieval through entity extraction from LLM
• Added Invoke operator for Agent
• Added support for DIFY external knowledge base API
• Added integration for ChatGPT-on-WeChat
• Added support for GLM4-9B, Yi-Lightning

What's Changed

• added tests.yml by @yuzhichang in #2685
• fix tests.yml by @yuzhichang in #2688
• refine readme by @KevinHuSh in #2689
• format mind_map_extractor code by @yqkcn in #2686
• Simplify the usage of dict by @yqkcn in #2681
• remove unused import by @yqkcn in #2679
• Refactoring entity_resolution by @guoyuhao2330 in #2692
• fix error in exception by @KevinHuSh in #2694
• Updated Dockerfile by @yuzhichang in #2695
• fix: Fixed the issue where no error message was displayed when uploading a file that was too large #2258 by @cike8899 in #2697
• Updated Dockefile to use cache by @yuzhichang in #2703
• Fix Dockerfile for arm64 by @yuzhichang in #2705
• Updated Build Docker Image by @writinwaters in #2706
• Fix Dockerfile.slim by @yuzhichang in #2708
• Fix poetry cache by @yuzhichang in #2709
• docs: Migrate README to Compose V2 syntax by @anud18 in #2711
• build multi-arch image by @yuzhichang in #2710
• Fix/bedrock issues by @Omarlsg98 in #2718
• remove redeclared get_json_result func by @yqkcn in #2675
• fix re.escape problem by @KevinHuSh in #2735
• chore: update operators.py by @eltociear in #2724
• support sequence2txt and tts model in Xinference by @JobSmithManipulation in #2696
• Add query parts to lamp by @KevinHuSh in #2736
• feat: Add component TuShare #1739 by @cike8899 in #2745
• Fix LIGHTEN. Close #2723 by @yuzhichang in #2744
• expand rerank range by @KevinHuSh in #2746
• Modified download_deps.py by @yuzhichang in #2747
• Update azure_sas_conn.py - fixing container_url typo by @jstride in #2740
• solve knowledgegraph issue when calling gemini model by @JobSmithManipulation in #2738
• move import positions by @KevinHuSh in #2753
• feat: The same query conditions on the search page should not request the interface every time the mind map drawer is opened. #2759 by @cike8899 in #2760
• Initial draft of Python APIs by @writinwaters in #2719
• Fix component exesql by @guoyuhao2330 in #2754
• fix xinference add rerank model bug by @wangguo1230 in #2758
• Fix docx images by @guoyuhao2330 in #2756
• Docs:fix user guide links by @Howe829 in #2761
• feat: Add a note node to the agent canvas #2767 by @cike8899 in #2768
• HTTP API documents, part1 by @JinHai-CN in #2713
• Use slim image as the default by @JinHai-CN in #2772
• Fix README description by @JinHai-CN in #2773
• Fix README and some comments by @JinHai-CN in #2774
• fix: Large document thumbnail display failed by @chongchuanbing in #2763
• fix bedrock issue by @KevinHuSh in #2776
• fix: torch dependency start error by @chongchuanbing in #2777
• Fix error commands by @JinHai-CN in #2778
• trival by @KevinHuSh in #2779
• Refactor README on different docker version. by @JinHai-CN in #2775
• refine agent by @KevinHuSh in #2787
• Updated instructions on downloading RAGFlow Slim and RAGFlow all-in-one. by @writinwaters in #2785
• fix: Change document status with @tanstack/react-query #13306 by @cike8899 in #2788
• Refactor Dataset API by @Feiue in #2783
• feat: Arrange the form of generate, categorize, switch, retrieval operators vertically #1739 by @cike8899 in #2800
• support api-version and change default-model in adding azure-openai and openai by @JobSmithManipulation in #2799
• fix: document preview by @chongchuanbing in #2795
• reduce rerank batch size by @KevinHuSh in #2801
• Fixed broken links. by @writinwaters in #2805
• support chat model in huggingface by @JobSmithManipulation in #2802
• fix LIGHTEN issue by @KevinHuSh in #2806
• trival by @KevinHuSh in #2808
• fix chat and thumbnail bug by @chongchuanbing in #2803
• Refactor Chat API by @Feiue in #2804
• refine components retrieval and rewrite by @KevinHuSh in #2818
• Refactor API for document and session by @Feiue in #2819
• Updated dataset APIs by @writinwaters in #2820
• refine token similarity by @KevinHuSh in #2824
• feat: Add message_history_window_size to CategorizeForm #1739 by @cike8899 in #2826
• feat: Fix translation issue of message_history_window_size #1739 by @cike8899 in #2828
• Refactor Document API by @Feiue in #2833
• Updated chat APIs by @writinwaters in #2831
• let presentation do raptor by @KevinHuSh in #2838
• feat: Generate operator names in an auto-incremental manner #1739 by @cike8899 in #2844
• refine API token application by @KevinHuSh in #2847
• refactor api util by @KevinHuSh in #2849
• add rm token by @KevinHuSh in #2850
• Feat:Compatible with Dify's External Knowledge API by @Howe829 in #2848
• Enhance email validation: Allow top-level domains with 5 letters by @mrnicegyu11 in #2856
• refactor by @KevinHuSh in #2858
• Fix keys of Xinference deployed models, especially has the same model name with public hosted models. by @0000sir in #2832
• feat: API access key management #2846 by @cike8899 in #2865
• add API for tenant function by @KevinHuSh in #2866
• Refactor Chunk API by @Feiue in #2855
• Updated session APIs by @writinwaters in #2868
• update dashscope by @KevinHuSh in #2871
• feat: Configure the root directory alias #1739 by @cike8899 in #2875
• feat: Load markdown file with "asset/source" #1739 by @cike8899 in #2880
• Fixed docker build by @yuzhichang in #2881
• Draft: Updated file management-related APIs by @writinwaters in #2882
• Miscellaneous minor updates by @writinwaters in #2885
• feat: Bind data to TenantTable #2846 by @cike8899 in #2883
• add team tag to kb by @KevinHuSh in #2890
• Delete useless files by @Feiue in #2889
• feat: Use Badge.Ribbon to distinguish the teams to which the knowledge base belongs #2846 by @cike8899 in #2891
• add owner check for team wor...

RAGFlow-0.12.0

Summary

• Adds new Docker image of slim version will doesn't including embedding and reranker models.
• Improves the effect of long context conversion.
• Supports OpenTTS and SparkTSS
• Adds new Excel parsing method, user can choose the output data format between HTML and row text.
• User can remove the added model provider.

What's Changed

• Add Multi-Language Descriptions for 'Switch' Component and Update Message Assistant Placeholder by @Defozo in #2450
• fix ppt file from filemanager error by @KevinHuSh in #2470
• update document sdk by @JobSmithManipulation in #2445
• rename create_timestamp_flt to create_timestamp_float by @JobSmithManipulation in #2473
• fix superuser password not base64 encoded by @dadahsueh in #2475
• fix duplicated llm name betweeen different suppliers by @KevinHuSh in #2477
• rename some attributes in document sdk by @JobSmithManipulation in #2481
• fix parser for pptx of which files are from filemanager by @KevinHuSh in #2482
• update document sdk by @JobSmithManipulation in #2485
• fix(Add model api): Add VolcEngine to create api_key format error by @muzilib in #2490
• OpenAITTS by @Feiue in #2493
• refine TTS by @KevinHuSh in #2500
• Storage: Rename all the variables about get file to storage from minio. by @baifachuan in #2497
• Web: Display the icon of the currently used storage. by @baifachuan in #2504
• BugFix: Fixed api_key generation error for VolcEngine by @yungongzi in #2502
• refactor add LLM by @KevinHuSh in #2508
• remove setting-system/index.tsx error import by @muzilib in #2507
• Update README_zh.md by @AlvinCage in #2491
• fix self deployed llm lost by @KevinHuSh in #2510
• rm key set in xinference by @KevinHuSh in #2511
• make excel parsing configurable by @KevinHuSh in #2517
• refine reteival of multi-turn conversation by @KevinHuSh in #2520
• refine xinference by @KevinHuSh in #2521
• Rework Dockerfile.scratch by @yuzhichang in #2525
• fix: Add model by ollama in model provider page, user can't choose the model in chat window. #2479 by @cike8899 in #2529
• Reverted replacing npm with yarn by @yuzhichang in #2531
• fix: Merge models of the same category #2479 by @cike8899 in #2536
• feat: Configurable for excel, html table or row based text #2516 by @cike8899 in #2538
• feat: Refine reteival of multi-turn conversation #2362 by @cike8899 in #2539
• fix: Initial language is English, but the UI is in Chinese #2514 by @cike8899 in #2541
• fix component rewrite bug by @KevinHuSh in #2549
• Updated README on debugging web and python by @yuzhichang in #2544
• refine markdown prompt by @KevinHuSh in #2551
• SparkTTS by @Feiue in #2535
• refine using rerank model by @KevinHuSh in #2553
• Streaming output is supported, dialogue share is not by @writinwaters in #2555
• add an API of delete llm supplier by @KevinHuSh in #2556
• fix: Web code build fails on ARM machines #2554 by @cike8899 in #2557
• refine multi-turn chat in agent by @KevinHuSh in #2560
• feat: Add component YahooFinance #1739 by @cike8899 in #2561
• feat: Add component Jin10 #1739 by @cike8899 in #2563
• feat: Delete Model Provider #2376 by @cike8899 in #2565
• add lighten control by @KevinHuSh in #2567
• Fix tokenizer bug by @guoyuhao2330 in #2573
• multi-arch-build by @yuzhichang in #2571
• feat: If the model is not set, a pop-up window will remind the user #2295 by @cike8899 in #2574
• make it lighten by @KevinHuSh in #2577
• revert error in Dockerfile by @KevinHuSh in #2581
• Add template investment_advisor by @guoyuhao2330 in #2580
• trival by @KevinHuSh in #2582
• remove onnx copy command from dockerfile by @KevinHuSh in #2584
• deprecate init a super user by @KevinHuSh in #2589
• Add component Concentrator by @guoyuhao2330 in #2586
• Update dsl_examples and Fix component concentrator by @guoyuhao2330 in #2597
• Fix soft link. Close #2587 by @yuzhichang in #2602
• feat: Add component Concentrator #1739 by @cike8899 in #2604
• Fix: renrank_model and pdf_parser bugs | Update: session API by @Feiue in #2601
• Added two developer guide and removed from README ' builder docker image' and 'launch service from source' by @writinwaters in #2590
• fix AzureOpenAI issue` by @KevinHuSh in #2608
• Remove WenCai imageurl and update investment_advisor prompt by @guoyuhao2330 in #2606
• Support agent for aibot by @guoyuhao2330 in #2609
• fix generate bug by @KevinHuSh in #2614
• Bug fix - email processing could be run now from API by @adam-kobus in #2613
• force eml file to be parsed by EMAIL by @KevinHuSh in #2615
• Update Yichat base_url by @Feiue in #2620
• remove repeat func by @yqkcn in #2619
• style: fix typo and format code by @yqkcn in #2618
• fix: Fixed an issue where the first message would be displayed when sending the second message #2625 by @cike8899 in #2626
• Added doc on dev-slim by @yuzhichang in #2627
• add huggingface model by @JobSmithManipulation in #2624
• feat: Add top_n to DeepLForm #1739 by @cike8899 in #2629
• refine get_input by @KevinHuSh in #2630
• fix: Fixed the issue where the conversation list was not displayed on the conversation page #2625 by @cike8899 in #2638
• handle nits in task_executor by @yqkcn in #2637
• Fix logger error by @yqkcn in #2643
• change chunk.status to chunk.available by @JobSmithManipulation in #2646
• Fix mutable default argument by @yqkcn in #2635
• Refactoring large integers to improve readability by @yqkcn in #2636
• Add get_txt function by @yqkcn in #2639
• Add doc for dev image by @yuzhichang in #2641
• refine general purpose chat bot by @KevinHuSh in #2648
• rename get_txt to get_text by @KevinHuSh in #2649
• trival by @KevinHuSh in #2650
• fix template error by @KevinHuSh in #2653
• Updated component description by @writinwaters in #2651
• fix: Fixed the issue where the error message was not displayed when uploading a file that was too large #1782 by @cike8899 in #2654
• change url of local llm deploy guide by @JobSmithManipulation in #2659
• fix: Filter the timePeriod options based on the userType parameter #1739 by @cike8899 in #2657
• Add build image and launch from source in README by @JinHai-CN in #2658
• document preparation for release by @KevinHuSh in https://github....

RAGFlow-0.11.0

Summary

• Adds AI search, aiming to provide PerplexityAI for each enterprise.
• TTS output based on FishAudio, Tongyi Qwen TTS.
• Supports using Postgres instead of MySQL to store RAGFlow metadata.
• Supports using S3/Azure blob as file storage.
• Supports LLMs above Anthropic, Voyage AI, Google Cloud.
• Supports Tencent Cloud ASR, to convert speech files into text.
• Adds several financial-related agent operators.
• Adds a medical assistant agent.
• Adds RAGFlow evaluation benchmark, currently supported:
  • ms_marco_v1.1:https://huggingface.co/datasets/microsoft/ms_marco
  • trivia_qa:https://huggingface.co/datasets/mandarjoshi/trivia_qa
  • miracl:<https://huggingface.co/datasets/miracl/mira

What's Changed

• fix: Filter out disabled values ​​from the llm options #2072 by @cike8899 in #2073
• create dataset by @Feiue in #2074
• prepare for sdk http api by @KevinHuSh in #2075
• Update quickstart.mdx by @writinwaters in #2084
• Update license by @JinHai-CN in #2086
• feat: Add FeedbackModal #2088 by @cike8899 in #2089
• add message id to conversions by @KevinHuSh in #2090
• add inferface for message thumbup by @KevinHuSh in #2091
• add thumb up api by @KevinHuSh in #2092
• VolcEngine SDK V3 adaptation by @yungongzi in #2082
• Provide detailed error information. by @JinHai-CN in #2093
• alter way of alerting info of empty task by @KevinHuSh in #2094
• fix callback function error by @KevinHuSh in #2096
• add support for TTS model by @hangters in #2095
• add prompt to message by @KevinHuSh in #2099
• Fix API key validation api/conversation by @guoyuhao2330 in #2100
• fix no tts issue by @KevinHuSh in #2101
• update groq llm by @hangters in #2103
• add support for Tencent Cloud ASR by @hangters in #2102
• add tts api by @hangters in #2107
• add fish audio zh and zh-traditional by @hangters in #2109
• feat: Fetch conversation list by @tanstack/react-query and displays error message that task_executor does not exist #2088 by @cike8899 in #2112
• create and update dataset by @Feiue in #2110
• feat: Pop-up prompt message after modifying the dialog settings #2088 by @cike8899 in #2114
• feat: Modify the modal style of creating an agent so that there are more templates in the field of view #2122 by @cike8899 in #2123
• feat: Align the cards on the Model Providers page #2111 by @cike8899 in #2125
• fix the max token of Tongyi-Qianwen text-embedding-v3 model to 8k by @hwzhuhao in #2118
• fix: Delete the model.ts file of chat #1306 by @cike8899 in #2129
• make task resumable by @KevinHuSh in #2132
• Fix Text2SQL by @guoyuhao2330 in #2131
• remove alter log by @KevinHuSh in #2140
• fix: build on ARM #2137 by @netandreus in #2139
• fix(graphrag): variable refernence error by @dearjane in #2136
• Fix exeSQL component output by @guoyuhao2330 in #2141
• feat: Submit Feedback #2088 by @cike8899 in #2134
• optimize text parser by @KevinHuSh in #2144
• Fix Logical operator by @guoyuhao2330 in #2143
• feat: Show prompt send to LLM for assistant answer #2098 by @cike8899 in #2142
• alter message id by @KevinHuSh in #2146
• feat: Send message with uuid #2088 by @cike8899 in #2149
• Update Dockerfile.arm by @yangboz in #2150
• add support for Anthropic by @hangters in #2148
• add retry count to task by @KevinHuSh in #2152
• fix delete message error by @KevinHuSh in #2153
• complete implementation of dataset SDK by @Feiue in #2147
• feat: Delete message by id #2088 by @cike8899 in #2155
• Fix the issue about No module named 'graspologic' #2157 by @LiuHao-1443 in #2158
• add support for Voyage AI by @hangters in #2159
• Fix some security vulnerabilities. by @hangters in #2160
• fix anthropic bug by @hangters in #2161
• re-generate for conversation by @KevinHuSh in #2165
• feat: Regenerate chat message #2088 by @cike8899 in #2166
• feat: Hide the delete button on the agent page #2088 by @cike8899 in #2167
• Complete DataSet SDK implementation by @Feiue in #2171
• feat: Select derived messages from backend #2088 by @cike8899 in #2176
• ignore when save image fail by @KevinHuSh in #2178
• fix: Copied API link error #2188 by @cike8899 in #2189
• add support for Google Cloud by @hangters in #2175
• feat: add api of tenant app by @chinamerp in #2177
• fix: After sending the message for the first time, the returned content is not streamed out #2067 #1832 by @cike8899 in #2191
• Fixed a broken link by @writinwaters in #2190
• Fix component PubMed by @guoyuhao2330 in #2192
• fix folder name suffix checking` by @KevinHuSh in #2194
• fix tts interface error by @hangters in #2197
• Fix component PubMed by @guoyuhao2330 in #2195
• fix re sub bug by @KevinHuSh in #2199
• Update api.md by @JobSmithManipulation in #2196
• feat: Play audio #2088 by @cike8899 in #2200
• feat: add tenant api of create & delete user by @chinamerp in #2204
• feat: Add tts Switch to chat configuration modal #2088 by @cike8899 in #2206
• Minor editorial updates by @writinwaters in #2207
• enable 3 char words to finegrind tokenize by @KevinHuSh in #2210
• Add Authorization checks by @Feiue in #2209
• make term similarity robust by @KevinHuSh in #2212
• fix error response disformat usage by @KevinHuSh in #2213
• fix zhipuCV bug by @hangters in #2215
• Add Authorization checks by @Feiue in #2218
• fix tts add bug by @hangters in #2224
• feat: Supports pronunciation while outputting text #2088 by @cike8899 in #2227
• add stream chat with TTS by @KevinHuSh in #2228
• Fix bug : bad escape \x at position xxx (line xx, column xx) in agent by @guoyuhao2330 in #2226
• Add Authorization checks by @Feiue in #2221
• feat: Comment out tts item #2088 by @cike8899 in #2232
• Add Authorization checks by @Feiue in #2235
• Fix component qweather by @guoyuhao2330 in #2240
• fix QWenSeq2txt bug by @KevinHuSh in #2245
• fix issue wrong agent prologue for api by @KevinHuSh in #2246
• Add component yahoo finance by @guoyuhao2330 in #2244
• feat: Add SearchPage #2247 by @cike8899 in #2248
• Bump aiohttp from 3.9.4 to 3.10.2 by @dependabot in #2254
• Bump cryptography from 42.0.5 to 43.0.1 by @dependabot in #2253
• Bump n...

RAGFlow-0.10.0

Release Summary

• Supports text to SQL by RAG
• Provides Agent API
• Provide the health check on task_executor process.
• Add more Agent operator: Github, DeepL, BaiduFanyi, QWeather, ExecSQL, GoogleScholar
• Supports file type: eml
• Supports embedding model: Cohere
• Supports more LLMs or model services : GPT-4o-mini, PerfXCloud, TogetherAI, Upstage, Novita.AI, 01.AI, SiliconFlow, XunFei Spark, Baidu Yiyan, Tencent Hunyuan

What's Changed

• refine loginfo about graprag progress by @KevinHuSh in #1823
• feat: Add GoogleScholar #918 by @cike8899 in #1818
• fix: align limitation with env by @Chunshan-Theta in #1819
• add supprot for OpenAI-API-Compatible llm by @hangters in #1787
• add support for eml file parser by @hangters in #1768
• fix #1816 by @KevinHuSh in #1829
• Fixed a broken link by @writinwaters in #1831
• feat: Move files in file manager #1826 by @cike8899 in #1837
• fix: Unable to create a new chat assistant after closing the edit modal #1833 by @cike8899 in #1838
• fix: Embedding error in file parsing #1835 by @cike8899 in #1839
• fix: Entity types are only displayed when the knowledge graph is selected #1594 by @cike8899 in #1841
• add callback to entity extraction by @KevinHuSh in #1843
• refine mindmap by @KevinHuSh in #1844
• fix LocalAI add bug by @hangters in #1851
• add support for cohere by @hangters in #1849
• fix add slef base url openai error by @KevinHuSh in #1854
• feat: Do not display arrow icons on leaf node of folders #1826 by @cike8899 in #1862
• fix: The size of operators created from agent templates is displayed incorrectly #1863 by @cike8899 in #1864
• Fix a "TypeError: expected string or buffer bug" in docx files extracted using Knowledge Graph.#1859 by @jiyegege in #1865
• add support for lepton by @hangters in #1866
• remove jina pack in requirement file to fix package conflict by @hangters in #1867
• fix: Reference markers in the context may be carried over into the next answer by @leecj in #1855
• add support for gpt-4o-mini by @AAlexDing in #1827
• Add GitHub, deepl, baidu-fanyi by @guoyuhao2330 in #1857
• fix code injection by @Lyutoon in #1868
• less text, better extraction by @KevinHuSh in #1869
• feat: Add component DeepL #1739 by @cike8899 in #1870
• feat: Add component GitHub #1739 by @cike8899 in #1871
• feat: Add component BaiduFanyi #1739 by @cike8899 in #1874
• Add component qweather by @guoyuhao2330 in #1873
• Update version and format by @JinHai-CN in #1878
• feat: Replace the LocalAi icon #762 by @cike8899 in #1875
• Enhance the robustness of the code by @hangters in #1879
• feat: Add component QWeather #1739 by @cike8899 in #1881
• add using jina deploy local llm in deploy_local_llm.mdx by @hangters in #1872
• fix: model type only support single value by @hangters in #1884
• add function: upload and parse by @KevinHuSh in #1889
• Add agent api by @guoyuhao2330 in #1888
• fix no modual error by @KevinHuSh in #1892
• rm qwen-v1-max by @KevinHuSh in #1894
• remove qwen-v1-max by @KevinHuSh in #1895
• feat: Expose the agent's chat window to third parties #1842 by @cike8899 in #1897
• Fix token list , stats in api app.py by @guoyuhao2330 in #1896
• add support for PerfXCloud by @hangters in #1883
• add support for TogetherAI by @hangters in #1890
• add support for Upstage by @hangters in #1902
• Fix agent non stream by @guoyuhao2330 in #1904
• add sql to naive parser by @KevinHuSh in #1908
• fix: When the component id is very long, the delete button of generate will be hidden #1906 by @cike8899 in #1907
• feat: Add delimiter field to naive parsing method #1909 by @cike8899 in #1911
• add support for novita.ai by @hangters in #1910
• fix: Chunks cannot be deleted #1912 by @cike8899 in #1913
• feat: Added explanation on the parsing method of knowledge graph #1594 by @cike8899 in #1916
• fix api argument error by @KevinHuSh in #1920
• fix: Error on chat api，<BadRequestKeyError '400: Bad Request'> #1918 by @cike8899 in #1923
• boost paralal of graphrag by @KevinHuSh in #1924
• fix parameter error by @KevinHuSh in #1925
• feat: After selecting the parsing method as knowledge graph, the delimiter and chunk token number are displayed. #1594 by @cike8899 in #1929
• Fix retrieval API error and add multi-kb search by @wingjson in #1928
• add support for SILICONFLOW by @hangters in #1926
• fix prefXCloud logo bug by @hangters in #1933
• feat: Modify PerfXCloud name #1853 by @cike8899 in #1931
• fix mind map bug by @KevinHuSh in #1934
• refine error log while chunking by @KevinHuSh in #1937
• refine llm init by @KevinHuSh in #1938
• fix empty graph issue by @KevinHuSh in #1939
• add doc ids to chat by @KevinHuSh in #1944
• feat: Supports chatting with files/images #1880 by @cike8899 in #1943
• requirements_dev.txt is useless by @KevinHuSh in #1945
• Format file format from Windows/dos to Unix by @JinHai-CN in #1949
• feat: Delete the file from the upload control of the message input box #1880 by @cike8899 in #1946
• add interface to get doc infos by doc ids by @KevinHuSh in #1950
• Refactor switch component by @guoyuhao2330 in #1940
• add support for 01.AI by @hangters in #1951
• Correct the incorrect description of the pre-installed models on the SILICONFLOW platform. by @morler in #1956
• feat: Add FileIcon #1880 by @cike8899 in #1960
• Update api.md by @guoyuhao2330 in #1961
• fix add Bedrock llm error by @hangters in #1952
• feat: Add MessageInput to the external chat page #1880 by @cike8899 in #1963
• feat: Delete the files uploaded in the external dialog box #1880 by @cike8899 in #1967
• Refactor user register by @JinHai-CN in #1962
• refine upload & parse by @KevinHuSh in #1969
• Refactor user registration by @JinHai-CN in #1970
• Refactor user register & login by @JinHai-CN in #1971
• fix OpenAI Embedding length error by @hangters in #1972
• Add component ExeSQL by @guoyuhao2330 in #1966
• fix: Opening file whose type is Knowledge Graph appear error with tsx #1975 by @cike8899 in #1978
• fix 01.ai url error by @hangters in #1977
• feat: Add component ExecSQL #1739 by @cike8899 in #1982
• feat: Add tip to loop of ExeSQL #1739 by @cike8899 in #1983
  *...

RAGFlow-0.9.0

Release Summary

1. Support GraphRAG
2. Add more Agent operators: keyword extraction, Baidu/duckduckgo/pubmed/wikipedia/bing/google search operators.
3. Add support for audio files (speech-to-text recognition).
4. Add support for Gemini, Groq and other LLMs.
5. Support for reranker provided by xinference.
6. Add support for LM studio/OpenRouter/LocalAI/Nvidia api and other inference frameworks/engines/services.

What's Changed

• feat: translate the to field #918 by @cike8899 in #1435
• feat: translate graph and chat text by @netyum in #1433
• Update README by @JinHai-CN in #1438
• feat: translate name of operator #918 by @cike8899 in #1437
• feat: display the debugging results of each operator in a pop-up window #918 by @cike8899 in #1445
• fix no resualt bugs by @KevinHuSh in #1448
• fix no resualt bugs by @KevinHuSh in #1449
• API doc: Correct Base URL and Dataset URL. by @cyhasuka in #1444
• fix pdf_parser content confusion by @guoyuhao2330 in #1458
• fix pdf_paser char content confusion by @guoyuhao2330 in #1462
• add support for Gemini by @hangters in #1465
• fix: Delete hardcode by @cyhasuka in #1464
• fix: monitor changes in the data.form field of the categorize and relevant operators and then synchronize them to the edge #918 by @cike8899 in #1469
• API: start parsing by @cecilia-uu in #1377
• feat: validate the name field of the categorize operator for duplicate names and nulls #918 by @cike8899 in #1471
• feat: support xinference rerank model by @hwzhuhao in #1466
• added SVG for Groq model model providers by @paresh2806 in #1470
• feat: add KeywordExtractForm and BaiduForm and DuckDuckGoForm #918 by @cike8899 in #1477
• fix bugs of rerank model with xinference by @KevinHuSh in #1481
• fix bug about divided by zero by @KevinHuSh in #1482
• add Gemini key by @hangters in #1480
• feat: modify DuckDuckGo's style #918 by @cike8899 in #1485
• feat: translate text from DuckDuckGo #918 by @cike8899 in #1486
• fix: add message_history_window_size to GenerateForm #1472 by @cike8899 in #1487
• Fix baidusearch and duckduckgosearch by @guoyuhao2330 in #1488
• fix ollama max token issue by @KevinHuSh in #1489
• feat: add llm Select to KeywordExtractForm #918 by @cike8899 in #1492
• refine db connection by @KevinHuSh in #1494
• refine db connection by @KevinHuSh in #1495
• refactor name of duckduckgo by @KevinHuSh in #1496
• fix duckduckgo.py by @guoyuhao2330 in #1497
• fix: fixed the issue where the greeting message could not be displayed when opening the debug window #918 by @cike8899 in #1499
• fix: fixed the issue where parameters of DuckDuckGo could not be saved to the backend after being dragged to the canvas #918 by @cike8899 in #1503
• Fix: Implement DOMPurify to sanitize HTML content before rendering by @dservian in #1498
• feat: remove dagre and elkjs #918 by @cike8899 in #1506
• fix: fixed the issue that the llm field in the KeywordExtract form had no default value by @cike8899 in #1510
• fix: Add Model Providers:Azure-OpenAI error #1402 by @cike8899 in #1512
• Add component Wikipedia by @guoyuhao2330 in #1513
• API: show status of parsing by @cecilia-uu in #1504
• Set wikipedia lang by @guoyuhao2330 in #1515
• feat: add Wikipedia operator #918 by @cike8899 in #1516
• Added supported LLMs by @writinwaters in #1517
• fix: fixed the issue of error when opening the canvas #918 by @cike8899 in #1520
• fix wikipedia language by @guoyuhao2330 in #1519
• fix bugs about multi input for generate by @KevinHuSh in #1525
• fix minimax bug by @KevinHuSh in #1528
• fix: Hundreds of chunks list can't choose page #1238 by @cike8899 in #1532
• fix the tokens error that occurred when adding the xinference model by @hwzhuhao in #1527
• 'load llm infomation from a json file and add support for OpenRouter' by @hangters in #1533
• fix: Bulk disable the chunk, the UI still shows they are enabled #1236 by @cike8899 in #1534
• hide referece when disable cite by @KevinHuSh in #1535
• remove dependency by @KevinHuSh in #1536
• fix minimax init error by @KevinHuSh in #1537
• feat: replace open-router.svg #1467 by @cike8899 in #1538
• API Documentation by @cecilia-uu in #1526
• Update requirements.txt with pybind11 2.13.1 by @voulkon in #1548
• Update the Dockerfile.cuda by @cnjack in #1545
• fix: add group id field to ApiKeyModal #1353 by @cike8899 in #1540
• fix emmpty input in graph by @KevinHuSh in #1560
• refine generate by @KevinHuSh in #1562
• Update deploy_local_llm.md by @cnjack in #1557
• Add templates/websearch assistant by @guoyuhao2330 in #1559
• Fix web search and template max tokens by @guoyuhao2330 in #1564
• fix: remove duplicate MessageItem #1289 by @cike8899 in #1566
• fix MiniMax api error by @hangters in #1567
• fix requirements.txt by @guoyuhao2330 in #1570
• API: Stop parsing by @cecilia-uu in #1556
• fix: new message appears in wrong chat window. #1289 by @cike8899 in #1571
• feat: change all file names to lowercase #1574 by @cike8899 in #1575
• [Bug]: IndentationError: unindent does not match any outer indentatio… by @narendra-bluebash in #1579
• Updated deploy a local llm using IPEX-LLM by @writinwaters in #1578
• Fix component debug by @guoyuhao2330 in #1583
• fix: display total items on chunk list page #900 by @cike8899 in #1584
• fix: Minimax API is error! #1353 by @cike8899 in #1585
• Add component pubmed by @guoyuhao2330 in #1586
• Add component arxiv by @guoyuhao2330 in #1587
• fix generate error by @KevinHuSh in #1590
• add docker-compose-gpu.yml to support gpu by @Seaver-Zhu in #1591
• feat: add PubMed operator #918 by @cike8899 in #1589
• fix: after logging out and entering the knowledge base page again, the data before still exists #1306 by @cike8899 in #1597
• fix embeding model for Azure by @KevinHuSh in #1601
• fix function create to slove chunk number wrong by @Seaver-Zhu in #1604
• Fix component exception by @guoyuhao2330 in #1603
• add support for LocalAI by @hangters in #1608
• fix: use @tanstack/react-query to get knowledge base data #1306 by @cike8899 in #1609
• fix delete selected chunks display wrong by @Seaver-Zhu in #1612
• add support for StepFun by @hangters in #1611
• Chat Use CVmodel by @guoyuhao2330 in #1607
• feat: support AWS Bedrock #308 by @ci...

RAGFlow-0.8.0

What's Changed

• Update README by @JinHai-CN in #1001
• fix bug 994 ,991 by @KevinHuSh in #1004
• fix #994 by @KevinHuSh in #1006
• Update info by @JinHai-CN in #1005
• Add file rag/svr/discord_svr.py by @guoyuhao2330 in #1008
• fix chunk modification bug by @KevinHuSh in #1011
• Adding the Minimax model by @cecilia-uu in #1009
• Update README_zh.md，typo by @ArtificialZeng in #997
• Update README by @JinHai-CN in #1014
• Fix: bug #991 by @chinamerp in #1013
• Add API for moving files by @aopstudio in #1016
• refine file select code by @KevinHuSh in #1021
• Update readme and add license by @JinHai-CN in #1018
• refine API request data processing by @KevinHuSh in #1031
• fix: fixed the problem that the api will be called directly after selecting the chat assistant picture by @cike8899 in #1034
• create the python sdk to return version by @cecilia-uu in #1039
• [doc] Updated document on max map count by @writinwaters in #1037
• Update SDK->sdk, and add create_dataset by @cecilia-uu in #1047
• added delete_dataset method by @cecilia-uu in #1051
• fix: change the address of the ollama document by @cike8899 in #1043
• delete SDK repo and edit readme by @cecilia-uu in #1054
• refine rerank by @KevinHuSh in #1056
• feat: add custom edge by @cike8899 in #1061
• add version to package volcengine by @KevinHuSh in #1062
• feat: fetch flow by @cike8899 in #1068
• add self-rag by @KevinHuSh in #1070
• feat: Support Password Access for ElasticSearch by @cklogic in #1072
• rm wrongly uploaded py by @KevinHuSh in #1073
• feat: run flow by @cike8899 in #1076
• feat: support Self-RAG #1069 by @cike8899 in #1079
• feat: modify the chinese translation of self-rag #1069 by @cike8899 in #1081
• The interface supported by Traditional Chinese is not complete #1074 by @cike8899 in #1082
• documentaion for self-rag by @KevinHuSh in #1080
• feat: add FlowChatBox #918 by @cike8899 in #1086
• fix: bug similarity() in YoudaoRerank by @chinamerp in #1084
• Updated Ollama part of local deployment by @writinwaters in #1066
• fix bug in api by @KevinHuSh in #1088
• Fixed a Docusaurus display issue by @writinwaters in #1089
• feat: watch graph change by @cike8899 in #1092
• fix: logger formater is not work by @chinamerp in #1090
• [doc] Updated default value of quote in 'get answers' by @writinwaters in #1093
• add preview gif by @KevinHuSh in #1097
• feat: add OperateDropdown and send debug message #918 by @cike8899 in #1095
• Update README by @JinHai-CN in #1101
• Add redis config by @JinHai-CN in #1104
• infinity: Update embedding_model.py by @michaelfeil in #1109
• Supports obtaining PDF documents from web pages by @fkzhao in #1107
• fix: hide web crawl menu item by @cike8899 in #1110
• API: create dataset by @JinHai-CN in #1106
• feat: generate uuid with human-id #918 by @cike8899 in #1111
• Updated the doc for configuring api key by @writinwaters in #1112
• feat: catch errors when sending messages #918 by @cike8899 in #1113
• feat: add icon to graph nodes #918 by @cike8899 in #1117
• [doc] Minor editorial updates. by @writinwaters in #1115
• feat: set the anchor points of all nodes to be enterable and exitable #918 by @cike8899 in #1119
• Update discord link by @JinHai-CN in #1123
• refactor by @KevinHuSh in #1124
• feat: when a node of the graph is selected, the border of the node is highlighted. #918 by @cike8899 in #1125
• fix multi-modual bug by @KevinHuSh in #1127
• feat: add delete menu to graph node #918 by @cike8899 in #1133
• feat: duplicate node #918 by @cike8899 in #1136
• fix file preview in file management by @KevinHuSh in #1151
• support graph by @KevinHuSh in #1152
• add support for mistral by @KevinHuSh in #1153
• Add pdf support for QA parser by @aopstudio in #1155
• refine doc about supporting PDF for Q&A by @KevinHuSh in #1160
• Fix VolcEngine BUG by @yungongzi in #1165
• Fix Docker image building failure on MacOS (ARM architecture) by @aopstudio in #1177
• upgrade version fix security bug by @rickywu in #1173
• create list_dataset api and tests by @cecilia-uu in #1138
• delete_dataset method and tests created by @cecilia-uu in #1186
• added documentation for api and fixed: duplicate get_dataset() by @cecilia-uu in #1190
• [doc] RAGFlow's api key never expires by @writinwaters in #1188
• added api documentation and added more tests by @cecilia-uu in #1194
• Add markdown support for QA parser by @aopstudio in #1180
• fix too long query exception by @KevinHuSh in #1195
• Remove the visibilty of RAGFlow API by @JinHai-CN in #1196
• [doc] Hid new API doc on docusaurus site by @writinwaters in #1198
• fixed: duplicate name by @cecilia-uu in #1202
• add README to graph by @KevinHuSh in #1211
• fix: using embd which user configured at knowledgebase by @chinamerp in #1163
• created get_dataset, update_dataset API and fixed: delete by @cecilia-uu in #1201
• fix:failed to Create new Chunk in database #1159 by @chinamerp in #1214
• Add docx support for QA parser by @aopstudio in #1213
• Add docx support for manual parser by @aopstudio in #1227
• polished doc for dataset API by @cecilia-uu in #1219
• feat: support json file by @chinamerp in #1217
• refine code to prevent exception by @KevinHuSh in #1231
• feat: grey out the team function #1221 by @cike8899 in #1244
• Create SECURITY.md by @William957-web in #1241
• Let json files support naive parsing methods #1245 by @cike8899 in #1247
• Place pdf's image at the correct position in QA parser by @aopstudio in #1235
• fix Rerank Vector Similarity Score by @guoyuhao2330 in #1249
• feat: format code before submitting it #1251 by @cike8899 in #1252
• Support displaying images in the chunks of docx files when using general parser by @aopstudio in #1253
• Update SECURITY.md by @William957-web in #1248
• Optimized the chat interface (including the chat API after sharing) by @yungongzi in #12...

ragflow-0.7.0

Major updates:

• Integrates BCE and BGE reranker models.
• Integrates Jina embedding and reranker models.
• Supports LLM Baichuan and VolcanoArk.
• Supports RAPTOR for better text retrieval.
• Adds a new API for removing documents.
• Supports a new file format: HTML.
• Supports the ARM platform.

What's Changed

• Fix missing docker image version prefix v. by @CamusGao in #855
• Updated Launch service from source by @writinwaters in #856
• fix: the site domain name in the Chat Bot API is hardcoded. #776 by @cike8899 in #859
• Reorganized docs for docusaurus publish by @writinwaters in #860
• fix: display specific error message when previewing file error #868 by @cike8899 in #869
• fixed a format issue for docusaurus publication by @writinwaters in #871
• Fixed a format issue by @writinwaters in #872
• Add api/list_kb_docs function and modify api/list_chunks by @guoyuhao2330 in #874
• fixed: The choices may be empty. by @dashi6174 in #876
• fix import error by @yonghuili1 in #877
• Add api.md:/api/list_kb_docs/ description by @guoyuhao2330 in #881
• Implements RAPTOR for better chunking #882 by @cike8899 in #883
• feat: remove the space before promptText by @cike8899 in #886
• Add /api/document/rm function by @guoyuhao2330 in #887
• Add support for VolcEngine - the current version supports SDK2 by @yungongzi in #885
• feat: RAPTOR is not displayed when the parsing method is picture. by @cike8899 in #897
• fixbug for computing 'not concating feature' by @xinzhuang in #896
• add raptor by @KevinHuSh in #899
• Update api_md document/rm by @guoyuhao2330 in #894
• feat: fixed issue with threshold translation #882 and add NodeContextMenu by @cike8899 in #906
• Fix some syntax errors, re not import by @dashi6174 in #904
• Update README by @JinHai-CN in #901
• Bug fix for volcengine by @yungongzi in #909
• The fasttext library is missing, and it is used in the operators.py file. by @dashi6174 in #925
• syntax error by @dashi6174 in #924
• feat: build react flow nodes and edges from mock data #918 by @cike8899 in #919
• fix raptor bugs by @KevinHuSh in #928
• Expanded list of locally deployed embedding models by @writinwaters in #930
• Remove duplicated FROM. by @CamusGao in #935
• Updated RESTful API Reference by @writinwaters in #908
• Update docnm_kwd to doc_name by @guoyuhao2330 in #939
• Add Dockerfile and requirements.txt for arm by @aopstudio in #936
• feat: test buildNodesAndEdgesFromDSLComponents by @cike8899 in #940
• minor editorial updates for clarity by @writinwaters in #941
• Added support for Baichuan LLM by @yungongzi in #934
• fix #917 #915 by @KevinHuSh in #946
• Add umap-learn, fasttext and volcengine in requirements_arm.txt by @aopstudio in #945
• fix: fixed the issue of 404 error in the user settings page of the demo site by @cike8899 in #948
• Fixed a docusaurus display issue by @writinwaters in #954
• Update README by @JinHai-CN in #956
• Expanded the supported LLM list by @writinwaters in #960
• feat: add FlowHeader and delete edge by @cike8899 in #959
• limit the system context length of conversation messages. by @KevinHuSh in #962
• feat: add rerank models to the project #724 #162 by @cike8899 in #966
• feat: add jina by @cike8899 in #967
• add rerank model by @KevinHuSh in #969
• fix: if the conversation name is too long, it will overflow the current item. #607 by @cike8899 in #972
• fix jina adding issure and term weight refinement by @KevinHuSh in #974
• Update README.md by @writinwaters in #976
• Update README.md by @writinwaters in #978
• Fix:After being idle for a while, new tasks need to be cancel and redo by @cklogic in #958
• Add support for HTML file by @aopstudio in #973
• fix create dialog bug by @KevinHuSh in #982
• fix: fixed the issue of error reporting when saving chat configuration #965 by @cike8899 in #984
• set ollama keep_alive by @KevinHuSh in #985
• fix bug in pdf parser by @KevinHuSh in #986
• fix bge rerank normalize issue by @KevinHuSh in #988
• fix tk_count undefine issue by @KevinHuSh in #996
• Update README by @JinHai-CN in #998

New Contributors

• @CamusGao made their first contribution in #855
• @yungongzi made their first contribution in #885
• @xinzhuang made their first contribution in #896
• @aopstudio made their first contribution in #936

Full Changelog: v0.6.0...v0.7.0

ragflow-0.6.0

Major updates:

• Streaming output.
• Text chunks retrieval API.
• Supports skipping layout recognition for general layout.
• Provide system components status monitoring.

What's Changed

• make sure the error will be recorded. by @KevinHuSh in #672
• make sure to raise exception if redis is not there by @KevinHuSh in #674
• fix coordinate error by @KevinHuSh in #686
• fix: fix uploaded file time error #680 by @cike8899 in #690
• Update faq.md by @guoyuhao2330 in #685
• truncate text to fitin embedding model by @KevinHuSh in #692
• 0509 faq by @writinwaters in #693
• fix disabled doc is still retreivalable by @KevinHuSh in #695
• Minor editorial updates by @writinwaters in #700
• Update README with Detailed WebUI Service Launch Instructions by @cklogic in #694
• feat: delete the added model #503 and display an error message when the requested file fails to parse #684 by @cike8899 in #708
• docs: update README_ja.md by @eltociear in #707
• Make the app name configurable even after the project is built by @cike8899 in #731
• let file in knowledgebases visible in file manager by @KevinHuSh in #714
• let index be batchly. by @KevinHuSh in #733
• Update readme by @JinHai-CN in #741
• fix: typo in user_app.py by @shaoyie in #740
• fix bug of get file by @KevinHuSh in #746
• Create quickstart.md by @writinwaters in #743
• Refactor method name by @JinHai-CN in #760
• fix: hide the add button when the folder is a knowledge base by @cike8899 in #765
• Miscellaneous updates by @writinwaters in #769
• Refactor message output format by @JinHai-CN in #772
• support gpt-4o by @KevinHuSh in #773
• feat: support GPT-4o #771 and hide the add button when the folder is a knowledge base by @cike8899 in #775
• Update README by @JinHai-CN in #779
• Updated document upload method by @guoyuhao2330 in #777
• fix bugs in searching file using keywords by @KevinHuSh in #780
• fix a string format error by @KevinHuSh in #781
• fix: remove Top K in retrieval testing #770 and if the document parsing fails, the error message returned by the backend is displayed by @cike8899 in #782
• fix: .knowledgebase folder can be deleted bug and change "Add file to knowledge base" to "Link file to knowledge base" bug by @cike8899 in #786
• Updated conversation_api.md document/upload by @guoyuhao2330 in #787
• Support for code files parse by @dashi6174 in #789
• Added file management guide by @writinwaters in #788
• Knowledge base search is case sensitive by @KevinHuSh in #797
• fix: can't capitalize file or folder name by @KevinHuSh in #798
• Fix a bug in 'assistant-setting.tsx' that causes the upload button to… by @achilou in #796
• add version by @KevinHuSh in #807
• add stream chat by @KevinHuSh in #811
• feat: Support for conversational streaming by @cike8899 in #809
• Initial draft of configure knowledge base by @writinwaters in #794
• Add 2 embeding models from OpenAI by @KevinHuSh in #812
• use smaller docker images by @KevinHuSh in #813
• fix stream chat for ollama by @KevinHuSh in #816
• feat: add feishu oauth by @yonghuili1 in #815
• fix too large thumbnail issue by @KevinHuSh in #817
• fix: thumbnails are too large in the chat box #818 by @cike8899 in #819
• fix data init error by @KevinHuSh in #820
• fix doc number miss-match issue by @KevinHuSh in #822
• Default language will be given according to the browse setting and also can be configured #801 by @cike8899 in #823
• add api/list_chunks function by @guoyuhao2330 in #821
• fix zhipuAI stream issue by @KevinHuSh in #825
• correct mismatched kb doc number by @KevinHuSh in #826
• add doc ids in API: completion by @KevinHuSh in #827
• refine doc about API: completion by @KevinHuSh in #829
• fix bug of chat without stream by @KevinHuSh in #830
• fix bug about removing KB. by @KevinHuSh in #839
• fix english query bug by @KevinHuSh in #840
• add locally deployed llm by @KevinHuSh in #841
• The default max tokens of 215 is too small, answers are often cut off.I will modify it to 512 to address this issue. by @dashi6174 in #845
• feat: display the version and backend service status on the page by @cike8899 in #848
• Set the number of task_executor processes through the environment variable WS. by @dashi6174 in #846
• Split Excel file into different chunks by @guoyuhao2330 in #847
• fix minio health bug by @KevinHuSh in #850
• Create start_chat.md by @writinwaters in #836
• Updated how to handle stalled file parsing by @writinwaters in #851
• Set the language default value of the language based on the LANG envi… by @dashi6174 in #853
• Update before release by @JinHai-CN in #854

New Contributors

• @guoyuhao2330 made their first contribution in #685
• @cklogic made their first contribution in #694
• @shaoyie made their first contribution in #740
• @dashi6174 made their first contribution in #789
• @achilou made their first contribution in #796
• @yonghuili1 made their first contribution in #815

Full Changelog: v0.5.0...v0.6.0

RAGFlow-0.5.0

RAGFlow v0.5.0 is released. The major updates in this release include improving scheduling mechanisms, a lot of bugs have been fixed, and new models such as DeepSeek-V2, being integrated.

What's Changed

• fix bug about fetching file from minio by @KevinHuSh in #574
• fix: display the current language directly at the top and do not disp… by @cike8899 in #579
• make cites in conversation API configurable by @KevinHuSh in #576
• remove default redis configuration by @KevinHuSh in #582
• refactor code by @KevinHuSh in #583
• fix exception in pdf parser by @KevinHuSh in #584
• refine document by using latest as version number by @KevinHuSh in #588
• Updated FAQ: Range of input length by @writinwaters in #594
• feat: add FlowCanvas by @cike8899 in #593
• refine code by @KevinHuSh in #595
• refine redis connection by @KevinHuSh in #599
• refine document upload by @KevinHuSh in #602
• fix: #567 use modal to upload files in the knowledge base by @cike8899 in #601
• refine docker layers by @KevinHuSh in #606
• fix: omit long file names by @cike8899 in #608
• fix disable and enable llm setting in dialog by @KevinHuSh in #616
• fix: fixed the issue that ModelSetting could not be saved #614 by @cike8899 in #617
• remove PyMuPDF by @KevinHuSh in #618
• Fix: missing 'redis' package in requirements.txt by @huangbaichao in #622
• Fix missing 'ollama' package in requirements.txt by @huangbaichao in #621
• refine code by @KevinHuSh in #626
• fix: filter knowledge list by keywords and clear the selected file list after the file is uploaded successfully and add ellipsis pattern to chunk list by @cike8899 in #628
• docs: Add instructions for launching service from source by @huangbaichao in #619
• remove redis by @KevinHuSh in #629
• Updated faq.md by @writinwaters in #636
• Update README badge by @writinwaters in #639
• fix: add spin to parsing status icon of dataset table by @cike8899 in #649
• Refactor: Use TaskStatus enum for task status handling by @huangbaichao in #646
• fix file encoding detection bug by @KevinHuSh in #653
• optimize srv broker and executor logic by @fkzhao in #630
• refine text decode by @KevinHuSh in #657
• fix bug by @KevinHuSh in #659
• refine doc for v0.5.0 by @KevinHuSh in #660
• fix bugs by @KevinHuSh in #662
• remove unused dependency by @KevinHuSh in #664
• fix task losting isssue by @KevinHuSh in #665
• add support for deepseek by @KevinHuSh in #668
• feat: support DeepSeek by @cike8899 in #667
• update docker file to support low version npm package by @KevinHuSh in #669
• Update README by @JinHai-CN in #670

New Contributors

• @fkzhao made their first contribution in #630

Full Changelog: v0.4.0...v0.5.0

RAGFlow-0.4.0

What's Changed

• add file management feature by @KevinHuSh in #560
• feat: translate FileManager #345 by @cike8899 in #558
• fix rename bug by @KevinHuSh in #562
• feat: add Tooltip to action icon of FileManager by @cike8899 in #561
• fix bug of file management by @KevinHuSh in #565
• Update version info by @JinHai-CN in #564

Full Changelog: v0.3.2...v0.4.0