v0.5.2

✨ Enhancements

• Support RAG SDK (#1322)
• Add Client and API v2 (#1316)
• Refactor datasource module (#1309)
• Support yi proxy LLM (#1303)
• Support rag retriever evaluation (#1291)
• Add support for multiple versions of the same model (#1246)

🐞 Bug fixes

• Fix sql format error (#1319)
• Fix awel check empty data bug (#1311)
• Fix the bug of doris missing comments (#1308)
• Fix ClickHouse default login bug (#1292)
• Fix agent loss message bug (#1283)
• Fixed the problem of loading only one plugin when there are multiple (#1282)

🛠️ Other improvements

• Add pylint for storage (#1298)
• Add pylint for DB-GPT rag lib (#1267)

Thank you to all our contributors for making this release possible!
@2976151305, @ASTLY123, @Aries-ckt, @fangyinc, @jsRuner, @lordk911 and @yhjun1026

v0.5.1

✨ Enhancements

• APIServer supports embeddings (#1256)
• AWEL flow supports dynamic parameters (#1251)
• Support Hive Conn (#1215)
• Dynamically loading dbgpts (#1211)
• Support Copy AWEL flow (#1200)
• Support default strategy batch sync. (#1196)
• Support gemma model (#1187)
• Support RAG chat flow (#1185)

🚀 Performance improvements

• Support load large document (#1233)
• Increase the accuracy of reading Excel (#1209)

🐞 Bug fixes

• Fix multi-turn dialogue bug (#1259)
• Fix knowledge_space_dao.update_knowledge_space call in Knowledge… (#1250)
• Fix scheduler shutdown (#1237)
• Fix typo error (#1228)
• Fix HTTP Trigger parse parameter bug (#1225)
• Fix switch strategy failed in Chinese env. (#1219)
• Fix milvus_store.py delete collection(#1212)
• Fix KnowledgeQueryResponse (#1202)
• Fix sql format error (#1199)

🛠️ Other improvements

• Upgrate v0.5.1 doc (#1265)
• Overview update & fix reference addr (#1263)
• New AWEL tutorial (#1245)
• Set default knowledge icon (#1244)
• Add new feature docs reference (#1238)
• Add docs and usage for v0.5.0 (#1216)
• Update comments for gender and pay_status fields in test_case_m… (#1198)

Thank you to all our contributors for making this release possible!
@0sengseng0, @2976151305, @Aralhi, @Aries-ckt, @NuoweiWang, @csunny, @darius-gs, @fangyinc, @fayfox, @jiangshengdev, @polBachelin and @xiuzhu9527

v0.5.0

✨ Enhancements

• Support more chat flows (#1180)
• Add rag awel operator view metadata. (#1174)
• App i18n (#1173)
• Gpts app v0.4 (#1169)
• Native data AI application framework based on AWEL+AGENT (#1152)

🐞 Bug fixes

• Fix api path error (#1165)

🛠️ Other improvements

• Add upgrade to v0.5.0 documents (#1176)
• Update description and dbgpts (#1162)
• Update charts display (#1149)

Thank you to all our contributors for making this release possible!
@Aralhi, @Aries-ckt, @csunny, @fangyinc, @Hzh_97, @lcxadml, @xuyuan23 and @yhjun1026

v0.4.7

✨ Enhancements

• Add support for Azure openAI (#1137)
• Add Jina Embeddings (#1105)
• Refactor for core SDK (#1092)
• Feat/sync docs (#1088)
• Add schema-linking awel example (#1081)

🐞 Bug fixes

• Fix MySQL Database not support DDL init and upgrade. (#1133)
• Fix default setting prompt with history messages (#1117)
• Fix examples/awel get model_name from model_config (#1112)
• Fix bug of sharing data across DAGs (#1102)
• Fix examples/awel default loading model text2vec-large-chinese issue (#1095)

🛠️ Other improvements

• Add documents for dbgpt core lib (#1129)
• Add contributor wall (#1111)
• Fix package name conflict error (#1099)

Thank you to all our contributors for making this release possible!
@Aries-ckt, @JoanFM, @csunny, @fangyinc, @junewgl, @lcxadml, @likenamehaojie and @xiuzhu9527

v0.4.6

✨ Enhancements

• UI component rendering in agent dialog mode (#1083)
• Support chat agent scene use dbgpts (#1075)
• Add retrieve summary agent for both local files and URLs (#1063)
• Add rag operators and rag awel examples (#1061)
• 🎨 Unified color theme, AntV light/dark theme switching, Antd first-screen style loading. (#1020)
• Add summary assistant checking (#1053)
• APP use new SDK component (#1050)
• Multi agents v0.1 (#1044)
• New MessageConverter and more AWEL operators (#1039)
• Add Summary Assistant Agent According to User's Question (#1023)

🐞 Bug fixes

• Fix summary support zhipu message_converter (#1085)
• Fix clean extra file & fix agents use zhipu (#1079)
• Fix awel embedding examples and delete unuseful code. (#1073)
• Fix fix sql component error in the web. (#1068)
• Fix device MPS load llama error (#1033)

🛠️ Other improvements

• Format agent code (#1077)
• Add pylint for DB-GPT core lib (#1076)
• Update wechat QR code (#1069)
• Refactor proxy LLM (#1064)
• Update wechat QRcode (#1046)
• Update chat_knowledge.md and wechat.jpg (#1035)

Thank you to all our contributors for making this release possible!
@2976151305, @Aries-ckt, @csunny, @fangyinc, @qidanrui and @yhjun1026

v0.4.5

✨ Enhancements

• Chunk add enable_merge parameter (#1014)
• Support Baichuan API (#1009)
• Add paper link and citation (#1006)
• Support SOLAR-10.7B-Instruct-v1.0 (#1001)
• Proxy model support count token (#996)
• Support multi round conversation operator (#986)
• RAG Refactor (#985)
• Multi agent sdk (#976)
• More AWEL operators and new prompt manager API (#972)
• Add new LLMClient and new build tools (#967)
• Add gemini support (#953)
• Support Mixtral-8x7B (#959)

🐞 Bug fixes

• Fix batch sync api error after switch segmentation strategy (#1029)
• Fix chatgpt message format bug (#1028)
• Fix delete Chroma by vector ids did not success (#1027)
• Fix .env should not build to static assets (#1012)
• Fix information_schema (#999)
• Fix chat_history_db mysql message query bug (#989)
• Fix default proxyllm generator function (#971)
• Fix wenxin config in .env.template (#965)
• Fix Move the last user's information to the end (#960)
• Fix clickhouse connect error fix (#958)

🛠️ Other improvements

• Move PR Template in .github folder to automatically generate PR Template for each PR (#1024)
• Add Template for Pull Request (#1022)
• Update author info (#1013)
• Improve build performance (#1011)
• Fix baichuan API pylint error (#1010)
• Update README.zh.md with slack (#1003)
• Fix typo and new pre-commit config (#987)

Thank you to all our contributors for making this release possible!
@Aralhi, @Aries-ckt, @TJJ120635, @baichuan-assistant, @csunny, @fangyinc, @Hzh_97, @jinhucheung, @junewgl, @qidanrui, @vvycaaa, @xtyuns, @yhjun1026 and @yihong0618

v0.4.4

✨ Enhancements

• Add API authentication for serve template (#950)
• Refactor storage system (#937)
• Support simple DB query for SDK (#917)
• The first refactored version for SDK release (#907)
• Add Apache Doris 2.0+ Database connector (#902)

🐞 Bug fixes

• Fix if we do not set glm config, we use default (#952)
• Fix: Doris icon broken (#949)
• Fix not create database bug (#946)
• Fix metadata mysql url bug (#941)
• Fix fschat and alembic log conflict (#919)
• Fix api /knowledge/space/list (#906)
• Fix database conn special symbols (#898)

🛠️ Other improvements

• Add dbgpt_hub usage documents (#955)
• Add python unit test workflows (#954)
• Add Issue close workflow (#948)
• Add frontend code to DB-GPT (#912)
• Add cli and api documents (#909)
• Add StarRocks web icon (#896)

Thank you to all our contributors for making this release possible!
@Aralhi, @Aries-ckt, @csunny, @fangyinc, @qidanrui, @xuyuan23, @yhjun1026, @yihong0618, @zfanswer, @zhanggongguan and ericggzhang

v0.4.3

✨ Enhancements

• ChatKnowledge add similarity score and query rewrite (#880)
• Migrate table chat_history and connect_config from duckdb to sqlite and mysql.(#880)
• Support system code for feedback and prompt (#873)
• Add StarRocks 2.5+ DB adapter (#872)
• Unified proxyllm apisecret (#862)
• MTB supports multi-user and multi-system fields (#854)
• Adapt for xunfei Spark LLM (#846)
• Support Yi-34B-Chat (#837)
• More support LLMs and modify benchmarks (#823)
• Add tests cases for dashboard (#818)
• Modify AWEL http trigger route function (#817)

🐞 Bug fixes

• Fix rdbms db summary (#885)
• Fix scene base 'of_mode' error (#881)
• Fix openai chatgpt api response error (#871)
• Fix api error when upload files (#866)
• Fix(Azure): fix index out of range error due to Azure Openai reponses an empty chunk at first (#820)
• Fix web history bug (#848)

🛠️ Other improvements

• Docs(smmf): multi-model usage and introduction (#883)
• Add debugging documents (#864)
• Remove .plugin.env.template (#884)
• SMMF introduction and usage (#878)
• Redirect documents to new version (#856)
• Rewrite docs use Docusaurus (#853)

Thank you to all our contributors for making this release possible!
@Hopshine, @csunny, @junewgl, @quqibing, @Aralhi, @Hzh_97, @Aries-ckt, @fangyinc, and @zfanswer

v0.4.2

✨ Enhancements

• Support new Agentic Workflow Expression Language(AWEL) (#803)
• AWEL supports http trigger and add some AWEL examples (#815)
• Add document summary (#809)
• Integrate ant-v (#809)
• Add LLM benchmarks code (#808)
• Support LLM model cache (#803)
• Support custom trace storage (#782)

🐞 Bug fixes

• Fix Milvus References (#809)
• Compatible with OpenAI 1.x.x, compatible with AzureOpenAI (#804)
• ChatExcel: Tongyi proxyllm response with 'InvalidParameter:User and assistant need to appear alternately in the message' (#781)
• Fix(ChatData):ClickHouse connection testing problem. (#784)

🛠️ Other improvements

• Lint: code and datasets clean (#811)
• Refinement of grammar issues in README.md (#807)
• Update overview (#795)

Thank you to all our contributors for making this release possible!
@AlphaHinex,@Hzh_97, @lcxadml, @hustcc , @GuangMingYouBei @Aries-ckt, @csunny, @dl-sdu, @fangyinc, @oushu1zhangxiangxuan1, @qidanrui, @yhjun1026 and @zhanghy-sketchzh

v0.4.1

✨ Enhancements

• More trace records for DB-GPT (#775)
• ChatKnowledge add reference (#773)
• Support OpenAI-Compatible RESTful APIs (#768)
• Support the DB-GPT-Hub trained mode (#760)
• Support AquilaChat2-34B (#747)
• Support configuration metadata database name in .env file (#741)
• Enhance server request processing performance (#722)

🐞 Bug fixes

• Fixe typos (#761)
• Fix text limit bug (#738)
• Fix some model missing stop tokens bug (#734)
• Fix ChatExcel Language confusion bug (#732)
• Rename internlm-20b to internlm-chat-20b (#713)

🛠️ Other improvements

• Deploy Document Refactor (#773)
• Corrected all grammatical errors in README.md (#749)
• Update README.md (#746)
• Add prompt management document(#740)
• Add RAG in action arch image (#717)

Thank you to all our contributors for making this release possible!
@0xrahul6, @Abhishekgupta204, @Aries-ckt, @Kerlinn, @alienishi, @chinmay7016, @cm-liushaodong, @csunny, @eltociear, @fangyinc, @hairyputtar, @nobunagaaa, @wangzaistone, @xiaoxidashen and @yhjun1026