Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improving the CoroutineRunnable class to use schedulers and support multiple in-flight messages #1292

Conversation

mdemoret-nv
Copy link
Contributor

@mdemoret-nv mdemoret-nv commented Oct 19, 2023

This PR does the following:

  1. Migrates many of the coroutine pieces over to MRC (will need Adding more coroutine components to support async generators and task containers MRC#408 to pass before merging)
  2. Improves the CoroutineRunnable class to use the Scheduler interface to support multiple messages at a time.
  3. Lays the groundwork for the new coroutine runnable type in MRC
  4. Updates the embedding model exporter to work with more model types (tested on intfloat/e5-large-v2, and all-MiniLM-L6-v2)
  5. Laying the groundwork for the agents pipeline architecture

Closes #1178 and Closes #1180

@mdemoret-nv mdemoret-nv added non-breaking Non-breaking change feature request New feature or request sherlock Issues/PRs related to Sherlock workflows and components labels Oct 19, 2023
@mdemoret-nv mdemoret-nv added this to the 23.11 - Sherlock milestone Oct 19, 2023
@mdemoret-nv mdemoret-nv requested a review from a team as a code owner October 19, 2023 04:03
@mdemoret-nv mdemoret-nv merged commit ed91a6a into nv-morpheus:fea-sherlock Oct 20, 2023
4 of 7 checks passed
@mdemoret-nv mdemoret-nv deleted the mdd_sherlock-improve-coroutine-runnable branch October 20, 2023 05:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature request New feature or request non-breaking Non-breaking change sherlock Issues/PRs related to Sherlock workflows and components
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

[FEA]: Create Langchain Prompt Generator [FEA]: Create LLM Engine Core Functionality
1 participant