Apache HugeGraph-AI 1.7.0 (Release)

What's Changed

• fix(llm): limit the length of log & improve the format by @diya-he in #121
• fix: pylint in ml by @MrJs133 in #125
• fix(lint): critical bug with pylint usage by @MrJs133 in #131
• feat(llm): added the process of text2gql in graphrag V1.0 by @vichayturen in #105
• fix(llm): multi vid k-neighbor query only return the data of first vid by @yc319 in #132
• refactor(llm): use pydantic-settings for config management by @ChenZiHong-Gavin in #122
• fix(llm): replace getenv usage to settings by @ChenZiHong-Gavin in #133
• fix(llm): support choose template in api by @HJ-Young in #135
• fix(ml): Correct header writing errors by @MrJs133 in #140
• fix(llm): update prompt to fit prefix cache by @HJ-Young in #137
• chore: enable pip cache by @imbajin in #142
• feat(llm): timely execute vid embedding & enhance some HTTP logic by @MrJs133 in #141
• fix(llm): extract_graph_data use wrong method by @MrJs133 in #145
• feat(llm): use retry from tenacity by @ChenZiHong-Gavin in #143
• refactor(llm): remove enable_gql logic in api & rag block by @HJ-Young in #148
• doc(client): update README for python-client/SDK by @HJ-Young in #150
• feat(llm): modify the summary info and enhance the request logic by @MrJs133 in #147
• feat(llm): automatic backup graph data timely by @MrJs133 in #151
• refactor(llm): add a button to backup data & count together by @MrJs133 in #153
• fix(llm): use empty str for llm config by @ChenZiHong-Gavin in #155
• refactor(llm): extract topk_per_keyword & topk_return_results to .env by @MrJs133 in #154
• feat(llm): modify clear buttons by @MrJs133 in #156
• feat(llm): support intent recognition V1 by @HJ-Young in #159
• refactor(llm): change vid embedding x:yy to yy & use multi-thread by @MrJs133 in #158
• refactor(llm): support mathjax in rag query block V1 by @MrJs133 in #157
• feat(llm): use poetry to manage the dependencies by @returnToInnocence in #149
• feat(llm): add post method for paths-api by @MrJs133 in #162
• refactor(llm): return schema.groovy first when backup graph data by @MrJs133 in #161
• fix(llm): update gremlin generate prompt to apply fuzzy match by @HJ-Young in #163
• fix(llm): enable fastapi auto reload function by @Aryankb in #164
• fix(llm): merge all logs into one file by @Aryankb in #171
• refactor: use uv for the CI action by @imbajin in #175
• refactor(llm): use EN prompt for keywords extraction by @imbajin in #174
• chore: add collaborators in asf config by @imbajin in #182
• feat(llm): support litellm LLM provider by @coderzc in #178
• feat(llm): support switch graph in api & add some query configs by @afterimagex in #184
• refactor(llm): improve graph extraction default prompt by @Kryst4lDem0ni4s in #187
• refactor(llm): replace vid by full vertexes info by @imbajin in #189
• feat(llm): support asynchronous streaming generation in rag block by using async_generator and asyncio.wait. by @vichayturen in #190
• feat(llm): Generalize the regex extraction func by @HJ-Young in #194
• feat(llm): create quick_start.md by @MrJs133 in #196
• feat(llm): support Docker & K8s deployment way by @afterimagex in #195
• chore(llm): multi-stage building in Dockerfile by @imbajin in #199
• chore: enable discussion & change merge way by @imbajin in #201
• fix(llm): fix tiny bugs & optimize reranker layout by @HJ-Young in #202
• fix(llm): enable tasks concurrency configs in Gradio by @Kryst4lDem0ni4s in #188
• feat(llm):support graph checking before updating vid embedding by @MrJs133 in #205
• fix(llm): Align regex extraction of json to json format of prompt by @Thespica in #211
• fix(clien): fix documentation sample code error by @Thespica in #219
• feat(llm):disable text2gql by default by @MrJs133 in #216
• chore(llm): use 4.1-mini and 0.01 temperature by default by @MrJs133 in #214
• refactor(llm): enhance the multi configs for LLM by @cgwer in #212
• feat(llm): Textbox to Code #217 by @mikumifa in #223
• refactor: replace the IP + Port with URL by @mingfang in #209
• chore(dependency): update gradio's version by @weijinglin in #235
• fix(llm): failed to remove vectors when updating vid embedding by @MrJs133 in #243
• chore(llm): use asyncio to get embeddings by @Mushrimpy in #215
• refactor(llm): change QPS -> RPM for timer decorator by @Ethereal-O in #241
• refactor(llm): support batch embedding by @weijinglin in #238
• chore(llm): using nuitka to provide a binary/perf way for the service by @weijinglin in #242
• chore(hg-llm): use uv instead poetry by @cgwer in #226
• fix(llm): skip empty chunk in LLM steaming mode by @MrJs133 in #245
• fix(llm): ollama batch embedding bug by @MrJs133 in #250
• refactor(llm): basic compatible in text2gremlin generation by @MrJs133 in #261
• fix(config): enhance config path handling and add project root validation by @weijinglin in #262
• Fix: fix Dockerfile to add pyproject.toml anchor file by @weijinglin in #266
• feat(vermeer): add vermeer python client for graph computing by @MrJs133 in #263
• refactor: use uv in client & ml modules & adapter the CI by @cgwer in #257
• refactor(vermeer): use uv to manage pkgs & update README by @imbajin in #272
• docs: synchronization with official documentation by @weijinglin in #273
• docs: fix grammar errors by @ChenZiHong-Gavin in #275
• docs: improve README clarity and deployment instructions by @weijinglin in #276
• fix(llm): limit the deps version to handle critical init problems by @imbajin in #279
• chore: add docker-compose deployment and improve container networking instructions by @weijinglin in #280
• feat(llm): support semi-automated prompt generation by @LRriver in #281
• feat(llm): support semi-automated generated graph schema by @Creeprime in #274
• docs: update docker compose command by @hezhangjian in #283
• chore: unify all modules with uv by @imbajin in https://github.com/apache/incubator-hugegr...

Apache HugeGraph(incubating) AI Release 1.5.0

What's Changed

• chore: reformat doc by @liuxiaocs7 in #36
• fix: fusiform_similarity test in traverser for server 1.3.0 by @liuxiaocs7 in #37
• feat: added local LLM API, changed the config displayed in the initial gradio demo, and added openai's apibase configuration. by @vichayturen in #41
• chore: add pr auto label by @ChenZiHong-Gavin in #42
• chore(deps): bump requests from 2.31.0 to 2.32.0 in /hugegraph-python-client by @dependabot in #45
• doc: update llm readme by @ChenZiHong-Gavin in #43
• feat: add version api & test by @ChenZiHong-Gavin in #44
• chore: introduce black for code format in github actions by @ChenZiHong-Gavin in #47
• chore(deps): bump urllib3 from 2.0.7 to 2.2.2 in /hugegraph-python-client by @dependabot in #51
• chore: add auth param for property_key.remove() by @simon824 in #52
• refact: support py 3.12 & improve the graph rag config experience by @imbajin in #53
• Introduced a simple demo of mixed index and text2gremlin demonstration. by @vichayturen in #54
• chore(deps): bump setuptools from 67.6.1 to 70.0.0 in /hugegraph-python-client by @dependabot in #55
• fix(llm): avoid generating config twice by @jasinliu in #56
• fix: change openai base url by @ChenZiHong-Gavin in #59
• fix(llm): use a proper template for default case by @imbajin in #57
• feat(client): support graphspace & refactor the request logic by @afterimagex in #61
• feat(llm): handle 'island nodes' extraction in 2-step graph queries and add asynchronous methods to the four types of generation functions in the rag web demo. by @vichayturen in #58
• doc: revise environment dependencies; update preparation by @returnToInnocence in #65
• feat(client): Implement new api & optimize code structure by @afterimagex in #63
• chore(client): fix pylint by @afterimagex in #66
• chore: enable merge option temporarily by @imbajin in #68
• feat(client): support graphspace & refactor all APIs by @imbajin in #67
• feat(llm): support basic rag api(v1) by @ChenZiHong-Gavin in #64
• feat(llm): add auth for fastapi and gradio by @ChenZiHong-Gavin in #70
• feat(llm): support word segmt extraction component & multi-files uploading by @vichayturen in #69
• feat(llm): support user-defined search template by @imbajin in #71
• feat: Add progress bars and print information for building vector indexes by @vichayturen in #74
• feat(llm): record token cost & qps by @ChenZiHong-Gavin in #72
• feat(llm): support record QPS by decorator by @ChenZiHong-Gavin in #76
• feat(llm): support multi reranker & enhance the UI by @jasinliu in #73
• feat(llm): support multi-QA test/generate by @jasinliu in #78
• refact(llm): separate user prompt configs by @returnToInnocence in #77
• feat: refactor the vector index & enhance the UI for building KG by @vichayturen in #75
• feat(llm): support graph_rag_recall api by @imbajin in #79
• chore: reconstruct web using tabs pages by @ChenZiHong-Gavin in #80
• docs: update readme by @ChenZiHong-Gavin in #81
• docs: enhance user friendly for README by @ChenZiHong-Gavin in #82
• fix: pylint for ci by @edw4rdyao in #86
• chore: update gradio to v4.43.0 by @ChenZiHong-Gavin in #85
• feat(llm): update openai dependency to 1.47 by @jasinliu in #88
• feat(llm): support multiple property_type & importing graph from the entire doc by @vichayturen in #84
• feat(client): support complete data type for PropertyKey by @imbajin in #93
• refactor(llm): enhance a string of graph query method by @imbajin in #89
• chore: update graph ai repo desc by @imbajin in #94
• fix(llm): update config in time after apply changes in UI by @returnToInnocence in #90
• fix(llm): handle the profile regenerate error by @returnToInnocence in #98
• fix: lowercase the repo label by @imbajin in #100
• feat(llm): support any openai-style api(standard) by @ChenZiHong-Gavin in #95
• docs(llm): update preparations and example codes by @vichayturen in #103
• docs(llm): update configuration file related by @returnToInnocence in #99
• doc: update info before release 1.5.0 by @imbajin in #106
• feat(ml): node emdedding, node classify and graph classify with models based on DGL by @edw4rdyao in #83
• chore(dist): add .gitattributes for exporting source package by @VGalaxies in #108
• chore(dist): exclude binary files when exporting source package by @VGalaxies in #109
• feat(ml): graph learning algorithm impl (10+) by @MrJs133 in #102
• refact(client): use rich handle for log by @imbajin in #111
• refactor: optimize the process of graph rag by @ChenZiHong-Gavin in #101
• chore: clean LICENSE for source code package by @imbajin in #104
• fix(ml): handle pylint warning by @MrJs133 in #113
• feat(llm): support log_block in RAG platform & rest-api by @diya-he in #110
• fix(rag): rag api critical bug & rename some params by @returnToInnocence in #114
• fix: null value detection on vid attributes by @ChenZiHong-Gavin in #115
• fix(llm): answer prompt None value effect by @returnToInnocence in #116
• fix(llm): correct e_cache type by @ChenZiHong-Gavin in #117
• feat(llm): separate multi llm configs/models by @HJ-Young in #112
• chore(dist): add license header for files under style directory by @VGalaxies in #118
• chore: enable allow-license & exclude style dir by @imbajin in #119
• refactor(llm): merge & update keyword extraction logic/prompt by @HJ-Young in #120

New Contributors

• @jasinliu made their first contribution in #56
• @afterimagex made their first contribution in #61
• @returnToInnocence made their first contribution in #65
• @edw4rdyao made their first contribution in #86
• @VGalaxies made their first contribution in #108
• @HJ-Young made their first contribution in #112

Full Changelog: 1.3.0...1.5.0

Apache HugeGraph(incubating) AI Release 1.3.0

What's Changed

• chore: add asf.yaml and ISSUE_TEMPLATE by @simon824 in #1
• fix invalid github label by @simon824 in #3
• feat: initialize hugegraph python client by @simon824 in #5
• Bump urllib3 from 2.0.3 to 2.0.7 in /hugegraph-python by @dependabot in #8
• chore: create .gitignore file for py by @imbajin in #9
• fix: import error by @Zony7 in #13
• feat(llm): knowledge graph construction by llm by @Zony7 in #7
• [fix] function getEdgeByPage(): the generated query url does not include the parameter page by @chenlixuan in #15
• refact: improve project structure & add some basic CI by @simon824 in #17
• fix: issue template by @Radeity in #23
• feat: introduce pylint for code analysis by @simon824 in #22
• fix: base-ref/head-ref missed in dependency-check-ci on branch push by @liuxiaocs7 in #25
• feat: initialize rag based on HugeGraph by @Ling-Yuchen in #20
• feat(client): add variables api and test by @liuxiaocs7 in #24
• feat: add llm wenxinyiyan & config util & spo_triple_extract by @simon824 in #27
• feat: add auth&metric&traverser&task api and ut by @simon824 in #28
• feat: refactor construct knowledge graph task by @simon824 in #29
• chore: Update LICENSE and NOTICE by @simon824 in #31
• feat: Introduce gradio for creating interactive and visual demo by @simon824 in #30
• Add setup.py for packaging by @simon824 in #32
• chore: add release scripts by @JackyYangPassion in #33
• chang file chmod 755 by @JackyYangPassion in #34
• chore: create DISCLAIMER file for ASF by @imbajin in #35

New Contributors

• @simon824 made their first contribution in #1
• @dependabot made their first contribution in #8
• @imbajin made their first contribution in #9
• @Zony7 made their first contribution in #13
• @chenlixuan made their first contribution in #15
• @Radeity made their first contribution in #23
• @liuxiaocs7 made their first contribution in #25
• @Ling-Yuchen made their first contribution in #20
• @JackyYangPassion made their first contribution in #33

Full Changelog: https://github.com/apache/incubator-hugegraph-ai/commits/1.3.0