-
**What problem or use case are you trying to solve?**
Create a coding agent that improves itself based on benchmarks. In addition to (potentially) getting better agent performance this will also ena…
-
Thanks for the collection of works about LLM agents, I'd like to kindly request that you consider adding our work **AgentSquare** to your repository.
AgentSquare is a novel LLM agent search framewo…
-
Hi,
In this requiremets should be updated so that openai should also be installed.
phi interanally using this.
I am getting error
> Traceback (most recent call last):
> File "/ai/awesome…
-
### Description
When using memory=True for a crew that uses Azure Open AI, there is an error creating long term memory.
### Steps to Reproduce
```
import os
from chromadb.utils.embedding_…
-
I am currently building an agent flow, where an LLM is deciding what to do next. The LLM generates JSON for a Condition node, and the Condition will reroute the flow based on the input of the LLM. The…
-
USING SDK
response = memgpt_client.send_message(
agent_id=agent_id,
message=prompt,
role="user",
)
--->
*llm_api/helpers.py:184: UserWarning: Failed …
-
### Description
llm = LLM(
model="custom-model-name",
base_url="https://api.your-provider.com/v1",
api_key="your-api-key"
)
agent = Agent(llm=llm, ...)
An error is reported when the…
-
**Is your feature request related to a problem? Please describe:**
After closely observing agentic developers like opendevin and recent swebench verified score of sonnet3.5+tools(no agent), it's clea…
-
### 🚀 The feature, motivation and pitch
I'm currently making an agent using LLM which required using external tools. There is step in completion where tools is required to be called but what kind of …
-
```
def load_tokenizer(self):
if self.tokenizer is None:
import transformers
name = _MOCK_TOKENIZER if _MOCK_TOKENIZER else (self.tokenizer_name or self.model…