v0.3.19

What's Changed

• Enable the chat prompt use using the openai_llm, llama_index_llm, and vllm_api by @vkehfdl1 in #1150
• Modify README.md with new badge and image by @vkehfdl1 in #1151
• fix the generator modules by @vkehfdl1 in #1153
• Fix few errors and dump version 0.3.19 by @vkehfdl1 in #1155

Full Changelog: v0.3.18...v0.3.19

v0.3.18

What's Changed

• Add chat_fstring module and support chat function in vllm. (+reasoning) by @vkehfdl1 in #1141
• Fix vLLM model_executor deletion error for newer vLLM versions by @Copilot in #1144
• Add comprehensive GitHub Copilot instructions for AutoRAG development by @Copilot in #1146
• Cohere version upgrade to v.3.18.0 by @vkehfdl1 in #1147
• dump version 0.3.18 by @vkehfdl1 in #1148

New Contributors

• @Copilot made their first contribution in #1144

Full Changelog: v0.3.17...v0.3.18

v0.3.17

What's Changed

• Huggingface model automatically don't use async mode while ingesting by @vkehfdl1 in #1126
• Add uv run sphinx-build in sphinx.yml by @vkehfdl1 in #1128
• change openai version to the latest and replace openai.resources.beta… by @vkehfdl1 in #1131
• Bump tj-actions/changed-files from 44 to 46 in /.github/workflows by @dependabot[bot] in #1129
• Bump redis from 4.5.1 to 4.5.4 in /api by @dependabot[bot] in #1083
• Divide retrieval module to 'hybrid', 'semantic' and 'lexical' by @vkehfdl1 in #1135
• dump version v0.3.17 by @vkehfdl1 in #1136
• try to use more latest pydantic version by @vkehfdl1 in #1139

New Contributors

• @dependabot[bot] made their first contribution in #1129

Full Changelog: v0.3.16...v0.3.17

v0.3.16

What's Changed

• Fix broken link in README.md by @zenoengine in #1098
• Correct Japanese prompts to be more natural. by @sappho192 in #1103
• prevent unicode decoder error. by @vkehfdl1 in #1108
• Add support for openai_like embedding model in semantic splitter llama_index module by @parssky in #1109
• Upgrade Chroma to the latest version + change to uv by @vkehfdl1 in #1111
• Remove auto-rag.com URL usage by @vkehfdl1 in #1116
• Resolve dependency conflicts and dump version 0.3.15 by @vkehfdl1 in #1119
• Fixed yaml file by @vkehfdl1 in #1121

New Contributors

• @zenoengine made their first contribution in #1098
• @sappho192 made their first contribution in #1103
• @parssky made their first contribution in #1109

Full Changelog: v0.3.14...v0.3.16

v0.3.14

What's Changed

• Make AutoRAG to Monorepo by @vkehfdl1 in #960
• Change install method to yarn install by @vkehfdl1 in #1090
• Run the GUI next.js application using docker compose by @vkehfdl1 in #1092
• Add gpt-4.5-preview model in openai_llm.py. by @minsing-jin in #1095
• dump version 0.3.14 by @vkehfdl1 in #1097

New Contributors

• @minsing-jin made their first contribution in #1095

Full Changelog: v0.3.13...v0.3.14

v0.3.13

What's Changed

• 🚑 fix: Update container image tags for API services to use the latest… by @hongsw in #1048
• remove embedding_model from kwargs for passage filter module by @rjwharry in #1043
• Add score and other metadatas at /v1/retrieve endpoint by @vkehfdl1 in #1055
• update sphinx github actions by @vkehfdl1 in #1059
• fix: Poetry shell failed due to incorrect pyproject.toml format by @korjsh in #1051
• feat: add intfloat/multilingual-e5-large-instruct to embedding model by @e7217 in #1061
• Add Cohere rerank model v3.5 by @vkehfdl1 in #1050
• feat: enable dynamic embedding models #1060 by @e7217 in #1063
• Implement Node Generator Module for vllm Serving API Integration by @korjsh in #1062
• add llama index's ollama embedding and fix type hint of embedding_model by @rjwharry in #1071
• fix: Issue(#1064) with same Items in parsed_result by Concatenating Each Parsed Result by @e7217 in #1066
• dump version v0.3.13 by @vkehfdl1 in #1075

New Contributors

• @korjsh made their first contribution in #1051

Full Changelog: v0.3.12...v0.3.13

v0.3.12

What's Changed

• At cli, the default api remote setting is False now by @vkehfdl1 in #1028
• [HotFix] AutoRAG api error fix by @vkehfdl1 in #1032
• docs: update Milvus configuration examples by @e7217 in #1030
• Add instruction about removal of file name related file name by @vkehfdl1 in #1038
• change file type logic by @bwook00 in #1044
• change parse_result parquet file name at all_files set True by @bwook00 in #1046

Full Changelog: v0.3.11...v0.3.12

v0.3.11

What's Changed

• docs[fix]: modify contents on upstage parser by @e7217 in #967
• Resolve Pydantic 2.10.0 conflict issue with latest LlamaIndex by @vkehfdl1 in #973
• �Add Qdrant vectorDB by @bwook00 in #976
• Replace to local embeddings at the gpu sample config YAML files by @vkehfdl1 in #988
• Add full YAML at vectorDB integration docs by @bwook00 in #994
• feat: Set parameters for Milvus using the configuration file #998 by @e7217 in #1001
• docs: add warning about AttributeError: vllm_model by @e7217 in #1014
• fix: refactor method to properly release vllm instance resources by @e7217 in #1012
• support parsing multiple types of documents at once by @bwook00 in #1015
• feat: add func to generate multiple quries by @e7217 in #1009
• Release/v0.3.11 by @vkehfdl1 in #1017

New Contributors

• @e7217 made their first contribution in #967

Full Changelog: v0.3.10...v0.3.11

v0.3.10

What's Changed

• Add Integration part at docs by @bwook00 in #939
• Update README.md by @bwook00 in #941
• Add Weaviate VectorDB by @bwook00 in #949
• add documentation for evaluate your custom rag by @vkehfdl1 in #953
• Add /v1/retrieve endpoint at API server by @vkehfdl1 in #954
• Add pinecone vector DB by @bwook00 in #955
• Add Couchbase VectorDB by @bwook00 in #961
• Release/v0.3.10 by @bwook00 in #964

Full Changelog: v0.3.9...v0.3.10

v0.3.9

What's Changed

• Edit documentation about data schema and descriptions by @vkehfdl1 in #905
• autorag —version by @vkehfdl1 in #913
• [Hotfix] fix hf space url at README.md by @bwook00 in #917
• ✨ feat: improve sample size handling in Validator class by @hongsw in #912
• Fix error that missing init of huggingface llm and ollama by @vkehfdl1 in #919
• Fix: added table_html variable initialization by @effortprogrammer in #920
• enhanced documentation at custom LLM models by @vkehfdl1 in #923
• just return original texts when there is no corresponding tokenizer a… by @vkehfdl1 in #931
• add Arxiv citation for our paper by @vkehfdl1 in #932
• delete tqdm by @bwook00 in #934
• add demojize with emoji package by @rjwharry in #935
• Release/v0.3.9 by @vkehfdl1 in #936

New Contributors

• @effortprogrammer made their first contribution in #920

Full Changelog: v0.3.8...v0.3.9