Comments (4)
We don't have a history of the goals but thanks for taking the time @thanpolas! The repetition is a problem we're working on, need to find a way to make it more solid.
from loopgpt.
Hey @thanpolas! Thanks a lot for trying out L♾️pGPT. We will work on fixing LoopGPT passing wrong arguments to google_search. For setting up the official google search, go to Google Programmable Search Engine, where you can create a custom search engine. Select "Search the entire web". This will give you your CUSTOM_SEARCH_ENGINE_ID
. And then you need to enable "Custom Search API" and provide the CUSTOM_SEARCH_ENGINE_ID
there too.
FYI, L♾️pGPT falls back on DuckDuckGo search (which doesn't require any API keys) if the official google search doesn't work (for example if you don't have all the api keys) so feel free to remove both API keys and it will automatically use DuckDuckGo search.
Let me know how it goes!
from loopgpt.
@thanpolas PS. It will also be great if you can tell us the goals that produced this result.
from loopgpt.
Thank you for this, I will submit a PR to include this information on the README.
As to the query I cannot exactly recall it, is there a history of goals stored somewhere?
I did try to force a search by giving the following goal:
search for 1 news rss feed and show it to me
First step it searched for the rss with google_search, however, I am not sure if the result that got returned was sourced from google or duck... and then something weird happened, it thought it showed me the results but only pasted the template tag, see bellow:
from loopgpt.
Related Issues (20)
- Browser Issue: preloaded using link preload but not used within a few seconds from the window's load event. Please make sure it has an appropriate `as` value and it is preloaded intentionally HOT 4
- Running from notebook HOT 2
- Enviroment file HOT 33
- agent = Agent(model="gpt-4") throws an error HOT 1
- Make this compatible with Marvin / Langchain HOT 1
- example usage with fastapi on the server HOT 1
- Spike in usage of tokens of Open AI API using gpt-4 model HOT 1
- It doesn't seem to read text files HOT 4
- AssertionError HOT 1
- Doesn't seem to notice when it hallucinates a command? HOT 1
- browser.py call to summarizer exceeds token limits
- Function call `agent.config()` throws an error if `agent.clear_state()` is called before it HOT 2
- Persistent Context Transfer Between Multiple Agents HOT 1
- Add SerpApi instead of direct Google Search
- Compatibility with Other Language Models
- Rate Limited Reached on Initial Install Running Example Script . . . HOT 2
- ImportError: cannot import name 'PROCEED_INPUT'
- Support More OpenAI Models Like gpt-3.5-turbo-16k
- bash:syntax error- Ubuntu pip install and install from source 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 loopgpt.