Releases: jlewi/foyle
Releases · jlewi/foyle
v0.0.16
What's Changed
- Generate Completions using Claude by @jlewi in #186
- Give each streaming generate request a unique trace id by @jlewi in #187
- Increase buffer size to fix bufio.Scanner: token too long by @jlewi in #189
- Log processing fixes for streaming by @jlewi in #190
- Add a traces service by @jlewi in #191
- Add GetLLMLogsRequest to look at actual LLM calls by @jlewi in #192
- Support loading markdown files for evaluation that don't have answers. by @jlewi in #193
- Update Foyle to filter exposition and return single code cell - Do well on single code cell generation by @jlewi in #194
- Update Runme Developer Docs. by @jlewi in #195
- Add a context id to streaming requests by @jlewi in #196
- Update the test. by @jlewi in #197
- Add an RPC to generate completions - Support FrontEnd using the connect protocol by @jlewi in #198
Full Changelog: v0.0.15...v0.0.16
v0.0.15
What's Changed
- Tech Note Auto Insert Suggested Cells by @jlewi in #161
- Update TN008 with details about GhostCells by @jlewi in #164
- Minor bugfixes by @jlewi in #165
- Server changes to support ghost cells and autocomplete by @jlewi in #166
- Publish protos to the BSR; upgrade buf to v2 config by @jlewi in #172
- Instrument the new AIService with OTEL connect so we generate trace ids. by @jlewi in #176
- Put technical notes on the website. by @jlewi in #177
- Level 1 Evals. by @jlewi in #181
- Prompt Tuning for Autocomplete by @jlewi in #184
Full Changelog: v0.0.14...v0.0.15
v0.0.14
v0.0.13
What's Changed
- Document how to use Honeycomb with Foyle and RunMe by @jlewi in #148
- Fix Honeycomb docs. by @jlewi in #149
- Fix link and add a video of using foyle and RunMe. by @jlewi in #150
- Support loading training examples from GCS by @jlewi in #152
- Add documentation about using BigQuery. by @jlewi in #156
Full Changelog: v0.0.12...v0.0.13
v0.0.12
What's Changed
- Update docs to explain how to use Foyle with RunMe by @jlewi in #129
- Update Evaluation Code To Work With Markdown Documents by @jlewi in #105
- Fix issues with evaluation code by @jlewi in #133
- Evaluation improvements to support RAG analysis by @jlewi in #138
- Continuous log processing by @jlewi in #139
- Blog effectiveness of human feedback. by @jlewi in #141
- Remove images by @jlewi in #142
- Continuous Learning by @jlewi in #146
Full Changelog: v0.0.11...v0.0.12
v0.0.11
What's Changed
- Add a playbook related to releasing. by @jlewi in #118
- Use ULIDs for block ids by @jlewi in #120
- Use Pebble and Protos For Traces and BlockLogs by @jlewi in #122
- Support Learning using RunMe logs by @jlewi in #121
- Fix retraining for RunMe by @jlewi in #124
Full Changelog: v0.0.10...v0.0.11
v0.0.10
What's Changed
- vscode-web-assets needs an ImageReplicator resource by @jlewi in #108
- Implement a gRPC service to generate cells for RunMe by @jlewi in #106
- Developer guide for Foyle and Runme by @jlewi in #115
- Use RunMe Deserialization code; handle indented code blocks by @jlewi in #116
- Improve logging of OpenAI errors by @jlewi in #117
Full Changelog: v0.0.9...v0.0.10
v0.0.9
What's Changed
- Fix bug in Application.ApplyPaths by @jlewi in #93
- Compute the normalized distance by @jlewi in #94
- Evaluation Results Data Explorer by @jlewi in #96
- Add some eval examples for honeycomb commands and replicate. by @jlewi in #100
- Blog post about how foyle learns by @jlewi in #101
- Include the vscode-web-assets image in each release by @jlewi in #102
- Add a tech note about integrating with RunMe by @jlewi in #98
- Assets download shouldn't use CWD if there is no config file by @jlewi in #107
Full Changelog: v0.0.8...v0.0.9
v0.0.8
What's Changed
Full Changelog: v0.0.7...v0.0.8
v0.0.7
What's Changed
- Prefactor: move BlockLog and LogEntry into api package by @jlewi in #70
- PWA to view logs by @jlewi in #69
- Enable google analytics. by @jlewi in #71
- Blog about logging human feedback by @jlewi in #74
- Add acknowledgements to blog post by @jlewi in #78
- Change file name to logfeedback by @jlewi in #79
- Fix link. by @jlewi in #80
- Learning from past mistakes by @jlewi in #83
- Eval by @jlewi in #87
Full Changelog: v0.0.6...v0.0.7