-
-
Notifications
You must be signed in to change notification settings - Fork 325
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
Add documentation on how to use Amazon Bedrock #936
Conversation
Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models.
for more information, see https://pre-commit.ci
* fix settings save * show placeholder message when API keys section is empty
Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models.
for more information, see https://pre-commit.ci
Added a link in the section on Amazon Bedrock Usage in the docs to a subpage titled `Using Amazon Bedrock with Jupyter AI` which offers a detailed workflow for using Bedrock models, fine tuning them, and calling them in Jupyter AI.
for more information, see https://pre-commit.ci
@JasonWeill Thanks for your comment ("I'm a bit concerned by how much we're adding that's specific to Amazon Bedrock, including screenshots of the console, instead of deferring to the AWS docs. I'm wondering if we could solicit a review from someone outside AWS, to get an impartial opinion about this"). I have shortened the main user documentation to include only usage in Jupyter AI, and linked it to a subpage where all Bedrock usage details are provided more extensively. Note the new screenshots above. |
There are two one-sentence paragraphs near the big table of model providers that say, "To use the Bedrock models, you need access to the Bedrock service. For more information, see the Amazon Bedrock Homepage. … To use Bedrock models, you will need to authenticate via boto3." It might be good to merge these two into one, and to either add a sentence with a link to the Bedrock subpage to the or replace these with a link to the Bedrock subpage. It might also be good to add a link to "Using Amazon Bedrock with Jupyter AI" to the top of the "Amazon Bedrock Usage" section, either in addition to or instead of the link at the bottom. The "<--Back" link doesn't look quite right, both because it doesn't use an actual arrow character like ← and because it sends the user back to a place where they may not have been — for example, if they landed on the "Using Amazon Bedrock with Jupyter AI" page from a search engine query. See #655 — this might be better suited for the curiously empty "Section Navigation" in the left pane, to display a hierarchy of documents. |
Addresses comment by Jason Weill
for more information, see https://pre-commit.ci
@JasonWeill Thanks so much for the comments. I have addressed them as follows: Edited the two one-sentence paragraphs down to a single one: Added an additional link to the top of the "Amazon Bedrock Usage" page just below the first introductory paragraph. Removed the vacant left panel that was unused. Addresses Issue #655 You are right, the "Back" button is not meaningful and unclear as to where it leads. I replaced it with an explicit link as shown |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you! This is a good improvement.
* Bedrock usage documentation Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models. * Bedrock docs * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix saving chat settings (jupyterlab#935) * fix settings save * show placeholder message when API keys section is empty * Bedrock usage documentation Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models. * Bedrock docs * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Subpage for Bedrock use Added a link in the section on Amazon Bedrock Usage in the docs to a subpage titled `Using Amazon Bedrock with Jupyter AI` which offers a detailed workflow for using Bedrock models, fine tuning them, and calling them in Jupyter AI. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Updates to user docs Addresses comment by Jason Weill * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: david qiu <[email protected]>
* Bedrock usage documentation Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models. * Bedrock docs * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix saving chat settings (jupyterlab#935) * fix settings save * show placeholder message when API keys section is empty * Bedrock usage documentation Added a new section to user documentation for the use of Amazon Bedrock models, both base models and customized models. * Bedrock docs * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Subpage for Bedrock use Added a link in the section on Amazon Bedrock Usage in the docs to a subpage titled `Using Amazon Bedrock with Jupyter AI` which offers a detailed workflow for using Bedrock models, fine tuning them, and calling them in Jupyter AI. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Updates to user docs Addresses comment by Jason Weill * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: david qiu <[email protected]>
Address Issue #924
Added docs to show how to use Amazon Bedrock models with Jupyter AI. Shows how to use both base models and custom models after fine-tuning, using the model
arn
(Amazon Resource Name). Results in an extra subsection in the User documentation:The same section now contains a separate link at the end of the section that directs the user to a subpage with very detailed workflows on setting up and using Amazon Bedrock with Jupyter AI, including how to fine tune a based model to create a custom model and then call the custom model from Jupyter AI. See:
Clicking through on this leads to the following web page:
A "Back" button is also provided to return to the main user documentation page as can be seen on the screenshot above.