Comments (7)
I created a PR #80 ;)
from chatfred.
Understood... especially now that I read the sub-text :) Sorry for the mis-understanding.
from chatfred.
Yes, please fix this... additionally, if I set it to a low number such as 1 or 2, it doesn't mind the setting. It just shows everything. IOW, it doesn't work :(
from chatfred.
Thanks for reporting this bug. Unfortunately, I am quite busy recently. Maybe someone wants to create a PR?
from chatfred.
Hey @Sponge-bink!
Thanks for your PR. I already created a new release: https://github.com/chrislemke/ChatFred/releases/tag/v1.5.2
@toolman11 Could you check if this fix is also solving your issue? Thanks!
from chatfred.
No change for me. I deleted the workflow, downloaded ChatFred-1.5.3.alfredworkflow and installed it, added API key, set the "ChatGPT history length" to 1, then 3, then 0, and the complete history is still there (no changes to the history list I see when I invoke Alfred and type "cf ". I'm using the latest (August 2nd, I believe) version of Alfred 5.
from chatfred.
That's not what that option means, it just control how many recent messages got to actually send to ChatGPT (to provide better context / cut down token usage). You will see many history messages from Alfred before you send the query, it's there so that you can reuse a prompt (hit Tab key) or just view the result again (hit Return).
What you are experiencing is an expected behavior.
from chatfred.
Related Issues (20)
- Azure OpenAI API support? HOT 1
- Ollama support
- Notifications "You exceeded your current quota, please check your plan and billing details." instead of proper responds. HOT 3
- Gallery version is outdated HOT 1
- Do you have any plan to support DALL-E 3? HOT 3
- Constant error message: hmm something is wrong with your request, try again later... HOT 14
- Instruct GPT Models Deprecated HOT 7
- Autocomplete for aliases HOT 1
- Add support for images using GPT4-vision
- support custom model
- No response, just large 💬 emoji HOT 8
- how to chat to the previous gpt reply? HOT 2
- Token overuse HOT 3
- Order when using the Universal action & combined prompts
- Use Chatfred with LocalAI server? HOT 3
- ChatGPT Aliases Should Search for Keyword Within the Prompt, Instead of the Other Way Around HOT 1
- Ability to edit system prompt HOT 4
- Is anyone experiencing problems with inputs being cutoff? HOT 3
- Streaming the Reply to Save Time HOT 2
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 chatfred.