-
Notifications
You must be signed in to change notification settings - Fork 145
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
feat: add reasoning engine + multimodal agent sample notebook #106
base: main
Are you sure you want to change the base?
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
LGTM |
View / edit / reply to this conversation on ReviewNB RajeshThallam commented on 2024-10-16T21:24:24Z
|
View / edit / reply to this conversation on ReviewNB RajeshThallam commented on 2024-10-16T21:24:25Z Add a cleanup step to delete datastore and deployed agent.
Check this notebook: https://github.com/GoogleCloudPlatform/applied-ai-engineering-samples/blob/main/research-operationalization/timesfm/operationalizing_timesfm_on_vertexai.ipynb |
@code-review-assist review the notebook |
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.
This pull request adds support for a reasoning engine and includes a sample notebook demonstrating a multimodal agent. This enhances the repository with valuable tools and examples. The documentation updates in mkdocs.yml
and the reasoning engine README effectively guide users. A minor suggestion for the .gitignore
file is to add a comment explaining the purpose of the added line. Overall, the changes are well-structured and contribute positively to the project.
scratchpad.md | ||
.idx/dev.nix |
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.
- Reasoning Engine: | ||
- Langchain on Reasoning Engine: | ||
- Overview: genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/README.md | ||
- Multimodal Support Concierge Agent: genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/multimodal_google_nest_support_agent_w_langchain_reasoning_engine.ipynb | ||
- Overview: genai-on-vertex-ai/vertex_ai_extensions/README.md |
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.
The "Overview" entry for Vertex AI Extensions is duplicated. While this might be intentional, it could be confusing. Consider removing the duplicate entry or adding a comment to clarify its purpose.
- Overview: genai-on-vertex-ai/vertex_ai_extensions/README.md | |
- Vertex AI Extensions: |
@@ -0,0 +1,5 @@ | |||
# Langchain on Vertex AI Reasoning Engine | |||
|
|||
In this set of notebooks, we will explore how to build an end to end agent with Langchain and deploy it on Vertex AI Reasoning Engine. |
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.
Minor suggestion: Change "end to end" to "end-to-end" for better readability.
In this set of notebooks, we will explore how to build an end to end agent with Langchain and deploy it on Vertex AI Reasoning Engine. | |
In this set of notebooks, we will explore how to build an end-to-end agent with Langchain and deploy it on Vertex AI Reasoning Engine. |
@code-review-assist Review jupyter notebook (.ipynb) |
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.
This pull request adds support for a reasoning engine and includes a sample notebook demonstrating a multimodal agent. This enhances the repository with valuable features for building more complex and interactive AI applications. The documentation updates in mkdocs.yml
and the README effectively reflect these additions. A minor suggestion for the .gitignore
file is to add a comment explaining the purpose of the ignored files. Overall, the changes are well-structured and contribute positively to the project.
scratchpad.md | ||
.idx/dev.nix |
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.
- Reasoning Engine: | ||
- Langchain on Reasoning Engine: | ||
- Overview: genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/README.md | ||
- Multimodal Support Concierge Agent: genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/multimodal_google_nest_support_agent_w_langchain_reasoning_engine.ipynb | ||
- Overview: genai-on-vertex-ai/vertex_ai_extensions/README.md |
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.
The "Overview" link appears twice under Agents. One of these entries should be removed to avoid redundancy and maintain clarity in the navigation structure.
- Overview: genai-on-vertex-ai/vertex_ai_extensions/README.md | |
- Vertex AI Extensions: | |
- Overview: genai-on-vertex-ai/vertex_ai_extensions/README.md |
|
||
In this set of notebooks, we will explore how to build an end to end agent with Langchain and deploy it on Vertex AI Reasoning Engine. | ||
|
||
1. [Multimodal Google Nest Support / Concierge Agent](genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/multimodal_google_nest_support_agent_w_langchain_reasoning_engine.ipynb) - This agent takes a video of the user describing their issues about Google Nest products, uses a combination of Gemini multimodality as well as Vertex AI Search to solve customer issues. |
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.
Using a relative path or the full URL to the notebook on GitHub would make the link more robust and platform-independent. Currently, the path assumes a specific directory structure, which might not be applicable in all contexts.
1. [Multimodal Google Nest Support / Concierge Agent](genai-on-vertex-ai/agents/reasoning_engine/langchain_on_reasoning_engine/multimodal_google_nest_support_agent_w_langchain_reasoning_engine.ipynb) - This agent takes a video of the user describing their issues about Google Nest products, uses a combination of Gemini multimodality as well as Vertex AI Search to solve customer issues. | |
1. [Multimodal Google Nest Support / Concierge Agent](./multimodal_google_nest_support_agent_w_langchain_reasoning_engine.ipynb) - This agent takes a video of the user describing their issues about Google Nest products, uses a combination of Gemini multimodality as well as Vertex AI Search to solve customer issues. |
No description provided.