-
**Describe the bug**
I want to test if the E2B sandbox executes all commands well, as it's required for LLM Agent to do anything, but some issues appear:
1. the `cd` command doesn't work. This may b…
-
Add notes here as things come-up -- current thinking is:
1. Make this a relatively quick demo (Cult of Done)
2. Use LLMs for interactivity -- e.g. custom train Llama or use GPT-4 based on semantic t…
-
RT
-
Based on https://python.langchain.com/docs/modules/agents/how_to/max_time_limit we can set a timeout for agents and a message will be returned to the user, this works in LangChain.
However when u…
-
Hello! When I tried to evaluate the ObjNav Benchmark, I found the following problems:
When I run
```
python objnav_benchmark.py --checkpoint="./checkpoints/pixelnav_A.ckpt"
```
Some errors emerge…
-
- [ ] introduce [Flowise](https://flowiseai.com/) in the loop
- [x] use local llm (ollama + compatible model)
- [ ] add vector storage to store retrieved POIs as embeddings, then use as retri…
-
I’m thinking about a more reliable solution for the webscraper, that as build in support for LLM commands to process the information on the fly.I found a project here: https://github.com/unclecode/cra…
-
### Issues Policy acknowledgement
- [X] I have read and agree to submit bug reports in accordance with the [issues policy](https://www.github.com/mlflow/mlflow/blob/master/ISSUE_POLICY.md)
### W…
-
### Describe the issue
Hi guys, I am currently using autogen multi-agent, multimodal, and function call for my project, my goal is to 1. convert code to image 2. get gpt-4 vision image feedback 3. im…
-
deepmind's SAFE agent (https://arxiv.org/pdf/2403.18802.pdf) using LLM Agent to split longform answers into multiple individual facts and check for factuality, in their benchmarks it is reported to be…