-
Hi!
Aider is an excellent tool, and as agentic software becomes more prevalent, I find that its shortfalls become more and more irritating. In a similar way that every computer is a slow horrible m…
-
Im running the stock example with open source models on Ollama. I have tried various open models (did not write my own modelfile) and it always ended up either delivering bad outputs, generating synta…
-
### Bug Description
I was trying to build a QA engine on SQL Database and Unstructured text, since Llama-index provides the connectivity Huggingface LLMs. I went with using that, when performing the …
-
### Is your feature request related to a problem? Please describe.
Currently, when a group chat terminates, there isn't a straightforward way to resume it, either by resuming the current `GroupChat` …
ekzhu updated
6 months ago
-
Is it possible to integrate XAgent with multi-agent frameworks like ChatDev and Autogen?
-
# Background research
## Readings
https://lilianweng.github.io/posts/2023-06-23-agent/
> * Finite context length: The restricted context capacity limits the inclusion of historical information, de…
-
### Feature Description
Multistep queries are great. But they can pollute the context window and cause the query path to be prematurely commited to one strategy.
As a more general paradigm, mult…
-
I'm implementing vectorstore agent on my custom data. Can I implement this with a local llm like gpt4all(GPT4All-J v1.3-groovy)
Can agents give better and expected answer when we use agents, or sho…
-
Any chance of integrating local LLMs through GPT4ALL, Oogabooga, LocalAI or connect to different model APIs (Claude)?
-
Initializing a store with the file backend breaks the gui. For a simple repro, I modified the example notebook `quickstart.ipynb` so that a store is initialized using a file backend. Changing https://…