Comments (8)
@HaroldMitts Sorry for the trouble. Let me try to solve it for you. First, let me know if your OpenAI Key starts with 'sk-'? Also, what is the commit id of the JARVIS you are using?
from jarvis.
I have quadruple checked my openai api key is correct. I copied and pasted it to avoid typo, I even generated a new key after many attempts/fails. However, no matter what key I generate and write to config.yaml, when I run awesome_chat.py it insists that I have an incorrect openai key.
I also tried running npm run dev and the browser opens and I see the HuggingGPT page and text box, but anytime I submit any prompt, system returns "Something seems seems wrong". Interestingly, localhost is opened to port 9999 when running npm run dev, but in config.yaml it has localhost port set to 8003.
What is it I am doing wrong? I feel like I am so close, but so far. :)
maybe you need to modify lite.yaml instead. when running python awesome_chat.py --config lite.yaml
the error message "Incrorrect OpenAI key. Please check your config.yaml file." is misleading, since it is actually using lite.yaml.
from jarvis.
@tricktreat The OpenAI API key does conform with the requirements and begins with sk- also, how do I check the commit ID?
@zzfoo I did try adding both keys to the lite.yaml and it is returning the same error
In general, I should be able to modify either yaml file key values, save the file(s), then rerun the commands to use either the browser or cli without restarting anything else, right?
from jarvis.
@HaroldMitts no, every time you change config.yaml, you need to run python awesome_chat.py --config config.yaml
again, the same go with lite.yaml
from jarvis.
Have I setup my lite.yaml
correctly? The config.yaml
uses the same convention where I have my keys in environment variables. You can see in the terminal where I print the keys (masked in the screenshot), to show the environment variables are set.
You can also see in the screenshot the error message
python awesome_chat.py --config config. yaml
Traceback (most recent call last):
File " /home/harold/Jarvis-4.6.2023/server/awesome_chat.py" , line 79, in <module>
raise valueError("Incrorrect OpenAI key. Please check your config.yaml file.")
ValueError: Incrorrect OpenAI key. Please check your config.yaml file.
I tried downloading Jarvis again using the code as of April 6th, but getting the same issues regardless if I hard-code my OpenAI API key into the lite and config yaml files, or use the environment variables.
Anytime I make changes in these yaml files, I run the awesome_chat script again.
from jarvis.
This is too strange. In fact, this error is only reported if the code is satisfied:
if not config["openai"]["key"].startswith("sk-") and config["openai"]["key"]!="gradio":
raise ValueError("Incrorrect OpenAI key. Please check your config.yaml file.")
from jarvis.
I added the double quotes around the hard-coded OpenAI API key and also around the Huggingface token, and it seems to have gotten past this issue.
I don't know if it is true, but if true, it seems like should be in the documentation.
from jarvis.
Following this, I think I will close this ticket. I got it working. Thanks for the help.
from jarvis.
Related Issues (20)
- 希望发布WINDOWS版
- Run command "npm run dev“, get npm Error. HOT 1
- Evaluation Dataset mentioned in Hugging GPT paper is not available HOT 1
- 运行python run_gradio_demo.py --config configs/config.gradio.yaml,报错:
- models_server.py error HOT 1
- Jarvis
- System : Failed to execute 'open' on 'XMLHttpRequest': Invalid URL HOT 1
- 这个项目不再更新了吗? HOT 2
- data目录下hg上llm的元数据文件p0_models.jsonl怎么获取
- No avaiable models, inference_mode: huggingface HOT 1
- Are there plans to release the task planning evaluation procedure and datasets? HOT 2
- Several questions.Whats the differences between the "tprompt" and "prompt" in config.yaml? HOT 1
- Jarvis
- M
- Idea to reduce resource usage in Microsoft/JARVIS
- keep getting Network Error response HOT 2
- windows 执行报错
- Don't retry same tool if already tried
- There is a runtime error in online demo. Please fix it.
- Function names in taskbench/generate_graph.py may be incorrect 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 jarvis.