Scribd
Upload
8 views1 page

SoW - LangChain AI Software Engineer

The document outlines a Statement of Work (SoW) for a Senior Software Engineer specializing in LangChain and AI, tasked with implementing a standard LLM-powered chatbot using Python in an AWS Lambda environment. The engineer will develop code to manage chat history in a DynamoDB database, retrieve user interactions, and generate responses using LangChain and a specified LLM. The estimated cost for this project is $7,500.

Uploaded by

annapojawis
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views1 page

SoW - LangChain AI Software Engineer

The document outlines a Statement of Work (SoW) for a Senior Software Engineer specializing in LangChain and AI, tasked with implementing a standard LLM-powered chatbot using Python in an AWS Lambda environment. The engineer will develop code to manage chat history in a DynamoDB database, retrieve user interactions, and generate responses using LangChain and a specified LLM. The estimated cost for this project is $7,500.

Uploaded by

annapojawis
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

SoW

Job Title: Senior Software Engineer - LangChain/AI Specialist (Python)

Implement a fairly “vanilla” / standard LLM-powered chatbot using LangChain in a Python


Lambda, which stores its history i a DynamoDB database.

Description of Work to be Completed:


● The engineer will write Python code (which will run in an AWS Lambda) that is invoked
from time to time by pMD’s application, either in response to user chats or to events
occurring within pMD’s application.
● When invoked, the Python code will be provided with an LLM prompt and a reference to
a DynamoDB database that stores chat transcripts (for conversation history) as well as a
summary of that user’s recent chats.
● With each invocation, the Python code will use LangChain’s
DynamoDBChatMessageHistory object to extract the most recent 10 messages from this
user’s transcript. It will also separately retrieve the summary of this user’s recent chats
from DynamoDB.
● Using LangChain, it will call a specified LLM AI such as ChatGPT to generate the
chatbot’s next response.
● The Python code will verify that the DynamoDBChatMessageHistory object is persisting
the new chats (user’s submission and chatbot’s reply) into DynamoDB. The Python code
should also separately use the ConversationSummaryBufferMemory object to update the
summary of the user’s recent interactions with the chatbot and then store the updated
summary in DynamoDB.
● Finally, the lambda should return the chatbot’s response.
● Please also provide a current version of the LangChain Python libraries in a format that
can be imported as a Layer in the AWS Lambda (example here).

Cost Estimate (either fixed cost or hourly):


● $7,500

You might also like