Research and summarization is the most popular agent use-case called out in our State of AI Agents report. But, conducting research and distilling the results into high quality reports is a time consulting and challenging task.
Here, we show how to build an agent that can orchestrate the end-to-end process of report planning, web research, and writing. We show that this agent can produce reports of varying and easily configurable format.
We build this agent using Llama 3.3-70b, the most recent of Meta's Llama models that matches the performance of 3.2-406b with 6x fewer parameters. We use NVIDIA NIM's inference service to access this model, taking advantage of LangChain integration with NIM.
Code:
https://github.com/langchain-ai/langchain-nvidia/blob/main/cookbook/structured_report_generation.ipynb
Blog: https://blog.langchain.dev/structured-report-generation-blueprint/
Video notes:
https://mirror-feeling-d80.notion.site/Multi-Agent-Architecture-w-Llama3-3-161808527b1780049531eafca071acde?pvs=4