Jerry Liu sur Twitter : "LLMs can directly extract structured data (esp w/ Function API), but can be slow/expensive. 🤔 Instead: use LLMs to generate code, run code to extract data..."
Tags:
About This Document
File info
Documents with similar tags (experimental)
Jerry Liu sur X : "Build a RAG backend over any website in a single CLI command ..."
Tags:
2024-02-03 About
LlamaIndex: "Instead of using a global fixed chunk size for RAG, try splitting based on the semantics of the text"
Tags:
2024-01-13 About
Jerry Liu sur X : "Naive chunking strategies cause poor RAG performance...."
Tags:
2023-12-06 About
Jerry Liu sur X : "evaluating RAG: purely evaluating retrieval metrics (MRR, precision) isn’t the whole picture - you need end-to-end response evals..."
Tags:
2023-09-26 About
Jerry Liu sur X : "A simple trick to improve retrieval for RAG 💡: Embed “references” to each text chunk instead of the chunk itself (e.g. smaller chunks, summaries)..."
Tags:
2023-09-06 About
Jerry Liu sur X : "how do you get a good retrieval dataset w/o spending a ton of money on human labels? Answer: use LLMs"
Tags:
2023-08-30 About
Jerry Liu sur X : "One major way to improve your RAG system is to fine-tune your embedding model"
Tags:
2023-08-25 About
Jerry Liu sur X : "8 key considerations for building *production-grade* LLM apps over your data (RAG)..."
Tags:
2023-08-20 About
Jerry Liu on X: “Graph RAG” in @llama_index: a new method of augmenting LLMs with context from a graph database
Tags:
2023-08-17 About
Jerry Liu sur Twitter : "Some critical data considerations that you must take into account to make your LLM application production-ready"
Tags:
2023-07-23 About
Jerry Liu sur Twitter : "if you have access to a rich query language (e.g. SQL / any DSL), use a vector db to index additional metadata to help the LLM execute queries using this query language, while preventing prompt overflows!
Tags:
2023-07-20 About
Jerry Liu sur Twitter : "Using cross-encoding as a reranking step can dramatically speed up LLM inference time AND improve accuracy!"
Tags:
2023-07-20 About
Jerry Liu sur Twitter : Hot take: if you want to... deliver technical differentiation, you will need to learn LLM development in a “bottoms-up” fashion
Tags:
2023-07-16 About
Jerry Liu sur Twitter : "Adding metadata to text can help w/ disambiguation and boost retrieval performance for LLM QA systems, using LLMs to... extract rich context to augment each chunk"
Tags:
2023-07-09 About
Jerry Liu sur Twitter : "If you’re building “chat over your PDFs” with LLMs, you need to deal with the pesky issue of how to parse embedded tables/diagrams..."
Tags:
2023-07-07 About
Jerry Liu sur Twitter : "The `camelot` package is an awesome module for extracting tables from PDFs..."
Tags:
2023-07-03 About
Jerry Liu sur Twitter : "The DSP project carries a lot of insights for improving RAG..."
Tags:
2023-06-18 About
Jerry Liu sur Twitter : "The new OpenAI Function API simplifies agent development by A LOT."
Tags:
2023-06-15 About
Jerry Liu sur Twitter : "LLMs + knowledge graphs backed by a graph db (@NebulaGraph). New stack for retrieval-augmented generation. Now possible with @llama_index..."
Tags:
2023-06-09 About
Jerry Liu sur Twitter : "Tuning top-k for semantic search is challenging... Introducing the LlamaIndex AutoRetriever for vector databases"
Tags:
2023-05-13 About
Jerry Liu sur Twitter : "LlamaIndex... has deep integrations with @MongoDB..."
Tags:
2023-05-11 About
Jerry Liu sur Twitter : "LlamaIndex: define your *own* (simplified) hybrid search"
Tags:
2023-04-29 About
Jerry Liu sur Twitter : "Building a Unified Query Interface. @gpt_index provides a crazy amount of functionality to make data retrieval + LLM’s really good for different use cases."
Tags:
2023-04-15 About
Jerry Liu sur Twitter : "To evaluate retrieval-augmented LLM’s, we can compare the query/response/source context to see if they match. We just added this to @gpt_index..."
Tags:
2023-04-11 About
Jerry Liu sur Twitter : "Sparse-Dense Hybrid Search..."
Tags:
2023-04-09 About
Jerry Liu sur Twitter : "A key goal of @gpt_index is to enable end users to ask an LLM *any* questions over their own data..."
Tags:
2023-02-27 About