Rohan
Professional AI Engineer. Sharing what I'm currently learning, mostly about AI, LLMs, RAG, building AI powered software, AI automation etc.
View on πThreads
Extract tables from documents using @llama_index UnstructuredElementParser and then use RecursiveRetriever to enable hybrid tabular/semantic queries and also comparisons over multi...
Finetuning the embedding model can allow for more meaningful embedding representations, leading to better retrieval performance. @llama_index has abstraction for finetuning senten...
We've seen that smaller chunks are good for capturing semantic meaning and larger ones are good for providing better context. @llama_index AutoMergingRetriever takes it one step f...
Previously we've seen @LangChainAI ParentDocumentRetriever that creates smaller chunks from a document and links them back to the initial documents during retrieval. MultiVectorRe...
Using #ChatGPT to easily create ChatGPT plugins π₯ #OpenAI #GPT4 #AI #python #fastapi A ChatGPT plugin consists of 3 things: 1. An HTTP server 2. An OpenAPI spec 3. A manifest file...