Large Refactor of Docs and Components #683
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
Collaborator
aaazzam
commented
Dec 15, 2023
•
aaazzam
commented
- makes components consume clients
- introduces Marvin.wrap to wrap openai client
- improves runtime settings
- isolates runtime settings from client generation
- adds updated documentation to account for all above
use settings for some defaults, avoid warnings
zzstoatzz
reviewed
Dec 15, 2023
Comment on lines
+253
to
+266
| When you do you'll see the raw payload that's sent to the LLM. The prompt you send is fully customizable. | ||
| ```json | ||
| { | ||
| "logit_bias": { | ||
| "15": 100.0, | ||
| "16": 100.0, | ||
| "17": 100.0, | ||
| "18": 100.0, | ||
| "19": 100.0, | ||
| "20": 100.0, | ||
| "21": 100.0, | ||
| "22": 100.0, | ||
| "23": 100.0 | ||
| }, |
zzstoatzz
reviewed
Dec 15, 2023
zzstoatzz
reviewed
Dec 15, 2023
|
|
||
| Marvin's goal is to bring the best practices for building dependable, observable software to generative AI. As the team behind [Prefect](https://github.com/prefecthq/prefect), which does something very similar for data engineers, we've poured years of open-source developer tool experience and lessons into Marvin's design. | ||
| This lets you focus on what you've always focused on: writing clean, versioned, reusable *code* and *data models*, | ||
| and not scrutinizing whether you begged your LLM hard enough to output JSON. |
There was a problem hiding this comment.
this is a matter of life and death
zzstoatzz
reviewed
Dec 15, 2023
zzstoatzz
reviewed
Dec 15, 2023
zzstoatzz
reviewed
Dec 15, 2023
| assert set(x.speakers) == set(["Adam", "Nate", "Jeremiah"]) | ||
| assert len(set(x.speakers)) == 5 | ||
| assert set(x.speakers) == set( | ||
| ["Adam", "Nate", "Jeremiah", "Marvin", "Billy Bob Thornton"] |
There was a problem hiding this comment.
hmm i was thinking i want my Literal to filter to only the speakers that I was interested in, so i purposefully left the extra person in the input out of the Literal to test that
There was a problem hiding this comment.
yeah, this is just a function calling regression / flaky test
happy to revisit
Co-authored-by: nate nowack <thrast36@gmail.com>
zzstoatzz
approved these changes
Dec 15, 2023
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.