One major drawback of semantic search is the inability to perform structured queries i.e. "What is the average dollar spend of our customers?"

One way to overcome this limitation is to combine AI's text-to-SQL for structured data with semantic search for unstructured data. For example, let's say you want to analyse cover letters of job applicants.

You've stored the full names and work experience (years) of each candidate in an SQL db and embedded the cover letters (alongside metadata containing full name of each candidate) in a vector db.

I built a GPT-4 'Warren Buffett' financial analyst to 'chat' with and analyze multiple PDF files (~1000 pages) across @elonmusk's Tesla 10-k annual reports (2020-2022)

#gpt4 #openai #investing #stocks #finance FYI this was powered by @LangChainAI , @pinecone and @OpenAI

I used the new GPT-4 api to 'chat' with a 56-page legal PDF document about the famous supreme court case: Morse v. Frederick

Powered by @LangChainAI and @pinecone

#openai #chatgpt #gpt4 #legal #lawyers #law Original PDF of legal case: tile.loc.gov/storage-servic…