this is pretty easily doable – you can give an agent access to multiple retrievers! https://
python.langchain.com/docs/use_cases
/question_answering/how_to/conversational_retrieval_agents
…
LLMS
-
Agents with Multiple Retrievers for Conversational QA
By
–
-
API now supports server-sent event streams for language models
By
–
Our API now supports server-sent event streams for language models, giving you live output as the model is running. Learn how to consume event streams to make your apps more responsive.
-
ParentDocumentRetriever balances chunk size for LLM optimization
By
–
We introduced the ParentDocumentRetriever last week to strike a balance between: – using small chunks during indexing
– passing larger chunks to the LLM Great overview and diagram by @clusteredbytes -
Self-Attention Mechanism in Large Language Models: From Scratch
By
–
Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch https://
bit.ly/3YL821l #AI #DeepLearning #MachineLearning #DataScience -
Apps Embracing Open Source Models for Better Integration
By
–
Love to see more apps adding support for open source models!
-
Llama 2 Demonstrates Surprising Tool Use Emergence
By
–
Tell Llama 2 about the tools it can use. It has surprising “tool use emergence.”
-
Temperature Settings for Creative vs Factual Llama Output
By
–
Play with the temperature. “A hot Llama never says the same thing twice.” Use higher temp for creative output, low for fact retrieval. Don't go too hot:
-
Llama 2 Model Sizes: Performance Trade-offs and Use Cases
By
–
As Llama 2 weight increases it gets slower and wiser. Much like Llamas in the real world. – 7b for summarizing or categorizing
– 13b for creative output
– 70b for anything involving nuance -
System Prompts: Optimize LLM Responses with Custom Instructions
By
–
Don't sleep on system prompts. – don't use the default
– use them to tell Llama who it should be or constraints for how to respond
– keep them short (they take up context window)
