-
Clean chat history before each question 2 of 3 checklist items completed
- Merged
-
-
- 14
- Approved
updated -
Collective LLM Judge 0 of 3 checklist items completed
- Merged
-
-
- 41
- Approved
updated -
Resolve "Adding Code Generation Open Source Datasets to Prompt Library for Chat Eval" 1 of 3 checklist items completed
- Merged
-
-
- 20
updated -
Build client and runner images in CI 0 of 3 checklist items completed
- Merged
-
-
- 1
- Approved
updated -
Added build target for the dataflow-runner container. 1 of 3 checklist items completed
- Merged
-
-
- 6
- Approved
updated -
Parameterize Duo Chat base url 0 of 3 checklist items completed
- Merged
-
-
- 7
- Approved
updated -
Containerize promptlib 1 of 3 checklist items completed
- Merged
-
-
- 87
- Approved
updated -
Add Anthropic claude-2.1 0 of 3 checklist items completed
- Merged
-
-
- 7
- Approved
updated -
Only publish wheel package 0 of 3 checklist items completed
- Merged
-
-
- Approved
updated -
Add the main evaluation pipeline for Duo Chat 1 of 3 checklist items completed
- Merged
-
-
- 25
- Approved
updated -
Add post-transformation to extract xml <completion> tag 1 of 3 checklist items completed
- Merged
-
-
- 3
- Approved
updated -
Config system 3 of 3 checklist items completed
- Merged
-
-
- 48
- 1
- Approved
updated -
Log pipeline progress with tqdm 0 of 3 checklist items completed
- Merged
-
-
- 5
- Approved
updated -
Add OpenAI GPT-3.5 models 1 of 3 checklist items completed
- Merged
-
-
- 4
- Approved
updated -
Add OpenAI GPT-4 models 0 of 3 checklist items completed
- Merged
-
-
- 13
updated -
Draft: Early days but this is an initial commit 0 of 3 checklist items completed
-
Store input/output for every transformation step. 2 of 3 checklist items completed
- Merged
-
-
- 30
- Approved
updated -
Support prompt templates on eval pipeline 1 of 3 checklist items completed
- Merged
-
-
- 41
- Approved
updated -
Add support for adding descriptions to the bigquery tables 1 of 3 checklist items completed
- Merged
-
-
- 11
- Approved
updated