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

update model name in these for making them eligible for multimodality #5777

Merged

Conversation

tanyaasharma
Copy link
Contributor

… models

Fixes # (issue)

@dosubot dosubot bot added the size:XS This PR changes 0-9 lines, ignoring generated files. label Jun 16, 2024
Copy link

vercel bot commented Jun 16, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
langchainjs-api-refs ✅ Ready (Inspect) Visit Preview 💬 Add feedback Jun 17, 2024 1:45pm
langchainjs-docs ✅ Ready (Inspect) Visit Preview Jun 17, 2024 1:45pm

Copy link
Contributor

@afirstenberg afirstenberg left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

None of the examples actually use multimodal inputs, so I'm not sure why the need to switch, but if we're going to, let's switch to the most recent releases that have stable versions and that also support general-purpose needs at reasonable prices.

@@ -25,7 +25,7 @@ const geminiCalculatorTool: GeminiTool = {

const model = new ChatVertexAI({
temperature: 0.7,
model: "gemini-1.0-pro",
model: "gemini-pro-vision",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggest "gemini-1.5-flash" or "gemini-1.5-flash-001" instead. (Pro Vision has been deprecated on the AI Studio side and will be supported for less time than 1.5 flash on the Vertex AI side.)

@@ -4,6 +4,7 @@ import { ChatVertexAI } from "@langchain/google-vertexai";

const model = new ChatVertexAI({
temperature: 0.7,
model: "gemini-1.5-pro-001",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

While 1.5 Pro is fine, 1.5 Flash might be a better general purpose suggestion for the examples (since it is significantly cheaper).

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You realize if you start adding models to this that your going to have to update it every time one gets deprecated.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fair point - however we can't update the class default without changing behavior so we generally put it explicitly. New models are infrequent enough where bumping all the strings isn't a huge issue.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we have a different definition of infrequent I would be willing to bet your looking at ever few months.

@@ -13,7 +13,7 @@ const calculatorSchema = z.object({

const model = new ChatVertexAI({
temperature: 0.7,
model: "gemini-1.0-pro",
model: "gemini-pro-vision",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggest "gemini-1.5-flash" or "gemini-1.5-flash-001" instead. (Pro Vision has been deprecated on the AI Studio side and will be supported for less time than 1.5 flash on the Vertex AI side.)

@@ -4,7 +4,7 @@ import { ChatVertexAI } from "@langchain/google-vertexai";

const model = new ChatVertexAI({
temperature: 0.7,
model: "gemini-1.0-pro",
model: "gemini-pro-vision",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggest "gemini-1.5-flash" or "gemini-1.5-flash-001" instead. (Pro Vision has been deprecated on the AI Studio side and will be supported for less time than 1.5 flash on the Vertex AI side.)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, Allen, i think you are right. Thank you, will update it

@jacoblee93
Copy link
Collaborator

Thank you!

@jacoblee93 jacoblee93 added the lgtm PRs that are ready to be merged as-is label Jun 17, 2024
@jacoblee93 jacoblee93 merged commit 7182ed6 into langchain-ai:main Jun 17, 2024
20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
lgtm PRs that are ready to be merged as-is size:XS This PR changes 0-9 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants