Re:LangChain Announces 10M Seed Round
by Jimmc414 on Tuesday April 04, 2023 @02:05PM
(#35443666)
Langchain allows an LLM to initiate query and prompt workflows and observing the results in a sequential or conditional logic chain or workflow and invoking agents, while GPT Index (now Llama Index) excels at connecting an LLM to external data sources and implementing creative indexing schemes for querying within given token context windows. Right now they both fill a need and complement each other nicely.
[ Parent
| on HN ]
Re:LangChain Announces 10M Seed Round
by bugglebeetle on Tuesday April 04, 2023 @02:18PM
(#35443850)
Do you have any good/interesting examples of these prompt workflows with langchain? I can see the utility in the abstract, but haven’t seen anything out in the world beyond clever toy projects.
This is a good cookbook style collection of notebooks that illustrate the Langchain functionality https://github.com/gkamradt/langchain-tutorials
Pinecone has some comparable langchain 'recipe' notebooks in their pinecone-io\examples Github repo
Re:LangChain Announces 10M Seed Round
by bugglebeetle on Tuesday April 04, 2023 @03:18PM
(#35444625)
Thank you! I’ll check these out!
Be careful out there when using Pinecone. The pricing seems to be confusing. https://twitter.com/Exploringfornow/status/16426070792852193...
Re:LangChain Announces 10M Seed Round
by bugglebeetle on Wednesday April 05, 2023 @12:52AM
(#35449446)
Yikes! Thanks for the heads up.
Entirely notional as of now, but I plan on testing it for game development. The thought is, you could create an embedding of the lore, data, facts and state of your game world and then interrogate the LLM about this in various ways. I see this being very useful both during the authoring of the game, and at runtime.
Re:LangChain Announces 10M Seed Round
by darkteflon on Wednesday April 05, 2023 @05:38AM
(#35451552)
That’s awesome, wonderful idea.
“State Machine games” is incredibly hard to Google!
I'm realizing I probably should update my bio on here more than once every decade! Currently working full time in a related industry, so most of my AI experimentations are strictly on my own time these days. If anyone is interested in these same sorts of things I am on twitter @TrevorJ