[11/N][RAG Demo fixes] add N-trial evals #1200
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jonathanlastmileai
requested review from
saqadri,
rholinshead,
suyoglastmileai,
Ankush-lastmile and
rossdanlm
as code owners
This was referenced Feb 8, 2024
Merged
jonathanlastmileai
added a commit
that referenced
this pull request
Feb 8, 2024
…ompts to prevent leak (#1196) [9/N][RAG Demo fixes] turn off remember chat context for remaining prompts to prevent leak --- Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/lastmile-ai/aiconfig/pull/1196). * #1200 * #1197 * __->__ #1196 * #1195
jonathanlastmileai
added a commit
that referenced
this pull request
Feb 8, 2024
…o indexing) (#1197) [10/N][RAG Demo fixes] go back to one of each prompt for each step (no indexing) --- Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/lastmile-ai/aiconfig/pull/1197). * #1200 * __->__ #1197 * #1196 * #1195
jonathanlastmileai
force-pushed
the
pr1200
branch
from
61d0346
to
bd815e4
Compare
This was referenced Feb 8, 2024
[13/N][RAG Demo fixes] [dev] aggregate metrics over all queries to review which dont work well
#1203
Merged
saqadri
added a commit
that referenced
this pull request
Feb 9, 2024
…1, generate_V2} (#1206) [15/N][RAG Demo fixes] [dev] benchmarking {gpt3.5,gpt4} X {generate_V1, generate_V2} 5 trials each. With GPT4, generate prompt v2 does slightly better on the benchmark. GPT3.5, V1 <img width="873" alt="v1-gpt3 5" src="https://github.com/lastmile-ai/aiconfig/assets/148090348/22b40ef8-b015-4185-8fcd-00dee4e295f3"> GPT3.5, V2 <img width="862" alt="v2-gpt-3 5" src="https://github.com/lastmile-ai/aiconfig/assets/148090348/73dca37d-c696-4d31-b604-febcfc89fbce"> GPT4, V1 <img width="879" alt="v1-gpt4" src="https://github.com/lastmile-ai/aiconfig/assets/148090348/8b5b7f0c-cefb-4332-90fe-d26a2a0bbf2d"> GPT4, V2 <img width="870" alt="v2-gpt4" src="https://github.com/lastmile-ai/aiconfig/assets/148090348/3a7f1825-a5ce-4c11-9c7e-04135b22b94a"> --- Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/lastmile-ai/aiconfig/pull/1206). * __->__ #1206 * #1204 * #1203 * #1202 * #1200
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
[11/N][RAG Demo fixes] add N-trial evals
Stack created with Sapling. Best reviewed with ReviewStack.