Comments (2)
Hi, you are right. As described in our paper, the adapters are used to "adapt language agent to real agent in application".
We follow Langchain in language agent implementation while modifying some parts to assist the application to be robust, such as truncation, streaming, and other issues discussed in paper Section3.2.
Back to your problem, some files are modified slightly by copying Langchain files and making what we want which pure Langchain package doesn't support. But they are necessary to the platform's performance.
from openagents.
@BlankCheng Thank you. I will read the paper carefully and catch the part you mentioned. Thanks for the explaination.
from openagents.
Related Issues (20)
- Unable to use my own uploaded files HOT 5
- How to change the port of the frontend to call the backend HOT 2
- when i run flask run -p 8000, some issues occurred HOT 2
- frontend error: Failed to fetch HOT 7
- How to integrate chatglm into the platform? HOT 1
- [BUG] Deleted file cannot be uploaded again HOT 5
- MultiProcess problem HOT 5
- how to connect app with sql DB? HOT 3
- `allowed_file` uploading bypass by simply changing file extension HOT 2
- how to extend a new llm for the agent? HOT 3
- Is there something works like session_id or user_id? HOT 4
- what version of langchain used
- Not able to run locally HOT 2
- xlang-code-interpreter-python HOT 3
- Data/Plugin Agent not working HOT 1
- Error: Failed to make the request MAPS HOT 9
- I cannot complete the installation. I can help by asking the openagents demo about the errors. HOT 1
- Error: Could not find kaggle.json HOT 2
- Do those plugins in the data agent support running locally? HOT 2
- FAQs about local deployment HOT 3
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 openagents.