-
I've noticed a common failure case is that Claude goes to edit a file but does not provide the full updated code. It's like "to be done" or even worse its discarding things because it puts "keep all f…
-
I am familiar with most of the flowise. I want the LLM chains to improve over time. For example, if the first chain generates an output, the second chain will review it and decide whether the quality …
-
### Describe the bug
When looking at time to first token in Langfuse the time is given as 12.41s whereas in reality the client started to see the response streaming back in under 3 seconds.
### To r…
-
There are existing agentic use-cases where it's important to have users accept or reject different actions before they are taken. For example, a travel bot that asks user confirmation before booking f…
-
## Some Context
I am using AI to build an agentic workflow using blazor on Dotnet 8 and ``` Microsoft.SemanticKernel``` Everything is working fine from the backend side.
I am creating a text complet…
-
**Is your feature request related to a problem?**
With Agents not able to run code generated by LLM.
Just like we have Tools for Index, Mapping, VectorDB, RAG, we can also have it for `Code Interpre…
-
Hello All,
I think it will be good to create examples using LLM gate, test_assist.metta and other hyperon tools, to show how to build an agentic LLM. Will that be useful? Any thoughts?
Cheers!
-
I just created a new application with version 0.1.25 and it looks like the system prompt setting from the .env file is ignored:
```typescript
// app/api/chat/engine/chat.ts
return new Context…
-
The following errors were reported by 5.6.0-dev.20240811, but not by 5.5.4
[Pipeline that generated this bug](https://typescript.visualstudio.com/TypeScript/_build?definitionId=48)
[Logs for the pipel…
-
at @onefact we have been using wasm, but this won't work for the encoder-only or encoder-decoder models i've built (e.g. http://arxiv.org/abs/1904.05342). that's because the wasm vm is for the cpu (ha…