I am getting this error

0
Chat with AI
0

hello
KeyError: 'session_id'
Traceback:

File "/Users/rupeshti/anaconda3/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 541, in _run_script
    exec(code, module.__dict__)
File "/Users/rupeshti/workdir/gitbox/langchain-aws-template-main/service/webapp/app.py", line 123, in <module>
    write_chat_message(a, q)
File "/Users/rupeshti/workdir/gitbox/langchain-aws-template-main/service/webapp/app.py", line 114, in write_chat_message
    st.session_state['session_id'] = md['answer']['session_id']
                                     ~~~~~~~~~~~~^^^^^^^^^^^^^^

Made with [Streamlit](http://streamlit.io/)

cdk deploy in the service blows up with some permissions errors

Full stack trace:

12:51:25 PM | CREATE_FAILED | AWS::Lambda::Function | LangChainHandlerDD6FD44B
Resource handler returned message: "User: arn:aws:sts::942747732415:assumed-role/cdk-hnb659fds-cfn-exec-role-9
42747732415-us-west-2/AWSCloudFormation is not authorized to perform: lambda:GetLayerVersion on resource: arn:
aws:lambda:us-east-1:177933569100:layer:AWS-Parameters-and-Secrets-Lambda-Extension:4 because no resource-base
d policy allows the lambda:GetLayerVersion action (Service: Lambda, Status Code: 403, Request ID: 64ab8809-cc5
4-49d2-996f-1b96c387404e)" (RequestToken: d53c00f6-d230-3dde-73bb-942b56d31849, HandlerErrorCode: AccessDenied
)

❌ LangChainApp failed: Error: The stack named LangChainApp failed creation, it may need to be manually deleted from the AWS console: ROLLBACK_COMPLETE: Resource handler returned message: "User: arn:aws:sts::942747732415:assumed-role/cdk-hnb659fds-cfn-exec-role-942747732415-us-west-2/AWSCloudFormation is not authorized to perform: lambda:GetLayerVersion on resource: arn:aws:lambda:us-east-1:177933569100:layer:AWS-Parameters-and-Secrets-Lambda-Extension:4 because no resource-based policy allows the lambda:GetLayerVersion action (Service: Lambda, Status Code: 403, Request ID: 64ab8809-cc54-49d2-996f-1b96c387404e)" (RequestToken: d53c00f6-d230-3dde-73bb-942b56d31849, HandlerErrorCode: AccessDenied)
at FullCloudFormationDeployment.monitorDeployment (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:397:10236)
at processTicksAndRejections (node:internal/process/task_queues:96:5)
at async deployStack2 (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:400:145739)
at async /Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:400:128776
at async run (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:400:126782)

❌ Deployment failed: Error: Stack Deployments Failed: Error: The stack named LangChainApp failed creation, it may need to be manually deleted from the AWS console: ROLLBACK_COMPLETE: Resource handler returned message: "User: arn:aws:sts::942747732415:assumed-role/cdk-hnb659fds-cfn-exec-role-942747732415-us-west-2/AWSCloudFormation is not authorized to perform: lambda:GetLayerVersion on resource: arn:aws:lambda:us-east-1:177933569100:layer:AWS-Parameters-and-Secrets-Lambda-Extension:4 because no resource-based policy allows the lambda:GetLayerVersion action (Service: Lambda, Status Code: 403, Request ID: 64ab8809-cc54-49d2-996f-1b96c387404e)" (RequestToken: d53c00f6-d230-3dde-73bb-942b56d31849, HandlerErrorCode: AccessDenied)
at deployStacks (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:400:129083)
at processTicksAndRejections (node:internal/process/task_queues:96:5)
at async CdkToolkit.deploy (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:400:147788)
at async exec4 (/Users/jmannix/.volta/tools/image/packages/aws-cdk/lib/node_modules/aws-cdk/lib/index.js:455:51984)

Stack Deployments Failed: Error: The stack named LangChainApp failed creation, it may need to be manually deleted from the AWS console: ROLLBACK_COMPLETE: Resource handler returned message: "User: arn:aws:sts::942747732415:assumed-role/cdk-hnb659fds-cfn-exec-role-942747732415-us-west-2/AWSCloudFormation is not authorized to perform: lambda:GetLayerVersion on resource: arn:aws:lambda:us-east-1:177933569100:layer:AWS-Parameters-and-Secrets-Lambda-Extension:4 because no resource-based policy allows the lambda:GetLayerVersion action (Service: Lambda, Status Code: 403, Request ID: 64ab8809-cc54-49d2-996f-1b96c387404e)" (RequestToken: d53c00f6-d230-3dde-73bb-942b56d31849, HandlerErrorCode: AccessDenied)

The AWS Secret needs to include 2 keys, the second slack-bot-token needs taken from the Slack App page in Slack after the app is configured. README should be updated to walk users through this.

To avoid timeouts and improve the user experience responses should be streamed using the streaming feature in Langchain and combined with WebSocket APIs

I think this issue is related to aws secrets manager not setup correctly, according to this issue.

I followed this instruction to set up my aws secrets (and I made sure that it was set up in the same region as my lambda & api):
Expected secret name is api-keys
openai key is expected to be stored with openai-api-key key

but I still got Status:502;Internal server error...

here is a log file:

logs.txt

Any help is appreciated!

Summary

Update the LangChain version to the current version 0.0.193.

Langflow is a web interface to experiment and prototype langchain pipelines.
https://pypi.org/project/langflow/

In Jupyter Notebook (jupyter notebook has docker).
Instructions : 5, 6, 7
langflow-ai/langflow#310
Got struck after installing. Both local and network links giving "This site can’t be reached"
Tried both with local and network ip adding /proxy/3000. Didn't work.

pip install langflow in sagemaker studio is exiting with the error below. Langflow not getting installed.

Add a Retrieval Augmented Generation (RAG) template that can connect to external knowledge sources.

Many developers will need a front-end login/authentication that integrates with the back-end. One option is Amplify authentication, but the downside is it requires a Javascript front-end. To do so we could look to making a Typescript front-end folder that branches off of the mckaywrigely/chatbot-ui project.

Amplify Auth has the added benefit of allowing developers to identify which user is currently accessing the front-end allowing them to customize the chatbot with multiple features such as: allowing a user to access previous conversations in the left-hand menu and ensuring a user only has access to their own data.

Another benefit of the mckaywrigely/chatbot-ui project front-end is we can add further features later on such as allowing a user to select certain tools (similar to GPT Plugins).