simpleaichat
AI
llm client library
SHOW HN2023
How HN took it
2 positive, 12 neutral or asking, 0 mixed, 1 critical, out of 15 comments about the project. Thread score +0.05.
Idea: 1 for, 1 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clean, developer-focused design that avoids bloat of LangChain and LlamaIndex
From 2 comments
Nice! Totally agree with the project goals, it seems too many other packages are created by people who are researchers (or enthusiasts) first and software developers second, and…
senko on HNI hope you keep investing in this project- it’s a crowded field but I do think existing projects like Langchain and LLamaindex feel very bloated and beyond a refactor - sometimes…
nextworddev on HN
Good work on the project
From 2 comments
Great work! I'd love to change this to use the new function logic in chatgpt
_private on HNNice work! Is there some JavaScript/Typescript alternatives to Langchain?
gautiert on HN
Objections
Does not retry on API errors out of the box
From 2 comments
Didn't find this in the README: does it handle network/OpenAI errors via retries? In particular the very common "model is overloaded at the moment". It's fine if not, I can…
H8crilA on HNErrors are so common with these endpoints, not having retry out of the box just makes it harder to hack on which I think is against the spirit?
mikeravkine on HN
Using GPT-4 API via a wrapper may conflict with ChatGPT terms
From 1 comment
Is interfacting with the GPT-4 API acting as if you are the ChatGPT UI against terms of service? I was under the impression it was and they had a bunch of methods to protect…
MuffinFlavored on HN
Requests
Support for local open source models
From 1 comment
Any chance your roadmap might include access to some local run open source models kind of like an oobabooga but with all your extra tooling baked in ?
jimmySixDOF on HN
Rate limiting and batch query handling
From 1 comment
Since this is async, can it automatically handle provided rate limits and batch queries appropriately? Seems like everyone has to roll their own on this and it’s much nicer to…
bravura on HN
Use the new ChatGPT function calling
From 1 comment
Great work! I'd love to change this to use the new function logic in chatgpt
_private on HN
Questions
Does it handle OpenAI errors via retries?
From 1 comment
Didn't find this in the README: does it handle network/OpenAI errors via retries? In particular the very common "model is overloaded at the moment". It's fine if not, I can…
H8crilA on HN
Is there a JavaScript/TypeScript alternative to LangChain?
From 1 comment
Nice work! Is there some JavaScript/Typescript alternatives to Langchain?
gautiert on HN
Can GPT-4 be given a whole codebase to query?
From 1 comment
Are we anywhere close to being able to give a whole codebase to GPT-4 and ask various things about it?
rane on HN
Alternatives named
LangChain
From 2 comments
I hope you keep investing in this project- it’s a crowded field but I do think existing projects like Langchain and LLamaindex feel very bloated and beyond a refactor - sometimes…
nextworddev on HNNice work! Is there some JavaScript/Typescript alternatives to Langchain?
gautiert on HN
LlamaIndex
From 1 comment
I hope you keep investing in this project- it’s a crowded field but I do think existing projects like Langchain and LLamaindex feel very bloated and beyond a refactor - sometimes…
nextworddev on HN
aider
From 1 comment
My open source CLI tool can do this, as well as make changes to the code. Here's a chat transcript that shows how you can use it to explore and then modify a public github repo…
anotherpaulg on HN
tenacity (for retries)
From 1 comment
I was mixed about putting it in the base package but you can get the same behavior with the tenacity package.
minimaxir on HN