AutoGPT
AutoGPT copied to clipboard
Significant-Gravitas
Support Vectara (https://vectara.com) as memory backend.
Add Vectara (https://vectara.com) as memory backend.
Vectara is an end-to-end LLM-powered search platform. Compared to other memory backends in AutoGPT that use OpenAI Ada to generate embeddings, Vectara uses its own state of the art models to generate embeddings. This provides high relevance search results. Thus, Vectara is not simply a vector database, but an end-to-end neural search platform.
Vectara has a generous free tier (50mb text).
Disclaimer: I am a Vectara employee, and happy to maintain this memory backend. I'm also looking into personally contributing to other parts of Auto-GPT, as well as how Vectara as an org can contribute.
The latest updates on your projects. Learn more about Vercel for Git ↗︎
1 Ignored Deployment
| Name | Status | Preview | Comments | Updated (UTC) |
|---|---|---|---|---|
| docs | ⬜️ Ignored (Inspect) | Visit Preview | Apr 28, 2023 9:16am |
![vercel[bot] avatar](https://avatars.githubusercontent.com/in/8329?v=4 "Published by a pub.dev verified publisher"){kind=small}
This PR exceeds the recommended size of 200 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
Codecov Report
Patch coverage: 22.31% and project coverage change: -4.62 :warning:
Comparison is base (
1772a01) 54.86% compared to head (55fc0d2) 50.25%.
:exclamation: Current head 55fc0d2 differs from pull request most recent head 6505b9c. Consider uploading reports for the commit 6505b9c to get more accurate results
Additional details and impacted files
@@ Coverage Diff @@
## master #3389 +/- ##
==========================================
- Coverage 54.86% 50.25% -4.62%
==========================================
Files 65 66 +1
Lines 3020 3134 +114
Branches 508 523 +15
==========================================
- Hits 1657 1575 -82
- Misses 1227 1430 +203
+ Partials 136 129 -7
| Impacted Files | Coverage Δ | |
|---|---|---|
| autogpt/memory/vectara.py | 19.26% <19.26%> (ø) |
|
| autogpt/memory/__init__.py | 41.93% <33.33%> (-1.47%) |
:arrow_down: |
| autogpt/config/config.py | 76.97% <100.00%> (+0.15%) |
:arrow_up: |
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.
![codecov[bot] avatar](https://avatars.githubusercontent.com/in/254?v=4 "Published by a pub.dev verified publisher"){kind=small}
This PR exceeds the recommended size of 200 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size
This PR exceeds the recommended size of 200 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size
Thank you for the prompt review. I've addressed all your comments. Please take another look.
This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.
Can you kindly take a look at this PR? I tried joining the AutoGPT Discord channel, but it keeps saying "Accept Invite", followed by "Whoops, unable to accept invite". Thanks.
This is a mass message from the AutoGPT core team. Our apologies for the ongoing delay in processing PRs. This is because we are re-architecting the AutoGPT core!
For more details (and for infor on joining our Discord), please refer to: https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting
Hey, I've marked this as don't merge until the Memory Fixes are in. Sorry to keep it on hold longer, just no real way to test/validate functionality until the fixes are in