What's Changed
- 📂 feat: Additional known File Extensions by @danny-avila in #183
- 🔃 refactor: Improve Document Loaders, add
langchain-ollamato Lite Build by @gafda in #170 - 🔧 fix: Handle Surrogate Character Errors When Hashing Documents by @caizixian in #199
- 📒 fix: Ignore invalid utf-8 characters when handling PDFs by @caizixian in #200
- 🏓 fix: improve csv loading and character encoding detection by @bariscant in #173
- 📙 feat:
/textroute for exclusively parsing text from documents by @danny-avila in #201 - 🤖 feat: Google GenAI Embeddings by @danny-avila in #202
- 🔧 chore: Improve Document Loader and Vector Store Logging by @danny-avila in #203
- 📦 chore: Bump
pypdfto v6.0.0 by @danny-avila in #204 - 🚰 feat: Stream Document Embeddings to Database in Batches by @MarcAmick in #214
- 📦 chore: Resolve Package Advisories by @danny-avila in #220
- 🔧 refactor: Document Processing and Health Check Functions by @danny-avila in #221
New Contributors
- @gafda made their first contribution in #170
- @caizixian made their first contribution in #199
- @bariscant made their first contribution in #173
- @MarcAmick made their first contribution in #214
Full Changelog: v0.6.0...v0.7.0