Comments (2)
The version I posted seems to consistently have a problem of reaching the max number of tokens configured into the llm, or LM Studio. I'm seeing it stop before 256 tokens. It should be possible to allow more tokens.
However, I'm thinking it might be better to restructure the output to not try to generate one whole csv for all the data. Rather, I'm going to try to generate one agent and one corresponding task at a time. Furthermore, I am thinking it might be better to try to use a crew to do all this.
from autocrew.
Thanks so much for your work on the OpenAI LLM.
I'm going to open a couple of separate issues to organise workflow better.
Feel free to fork this repo if you wish. It may be better to do this, so that you we can each issue pull requests for the code which is applicable regardless of the LLM used
from autocrew.
Related Issues (20)
- Provide compatibility with OpenAI HOT 1
- Summary of issues with individual scripts
- requirements.txt for langchain-community HOT 2
- Structuring CrewAI scripts to use the OpenAI api HOT 3
- c++ developer creates a bad Agent Name HOT 1
- Error in Autocrew 2.0.7: Role Component Missing in CSV Data HOT 10
- bad import HOT 2
- openai key is now needed. HOT 4
- version3 bug
- Allow Delegation should be Yes/No
- SyntaxError: cannot assign to expression here. Maybe you meant '==' instead of '='? HOT 2
- ValueError: Missing or incomplete data for "role" HOT 2
- AutoCrew failed during the script generation phase due to a specific error encountered when attempting to process the response from LLM + Log attached
- Error during saving crews - missing ollama folder. HOT 1
- Tutorial should mention about install requirements.txt file HOT 1
- Why insist on Ubuntu/WSL? HOT 5
- Autocrew+Ollama failures HOT 1
- ValueError: No CSV data found in the response HOT 2
- No script file found for the selected crew
- Any idea how to set OPENAI_BASE_URL and system proxy? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from autocrew.