How To Create AI Tools Fast (Less Than 2 Minutes)

@zimbabox please share your code via a public link on Github. Without viewing the entire code it is hard to help you.

Hi, there is nothing to share as the code, links and all the materials exist already on Github link that Hasan provided on his website, I have just used his code to see if it will work with me or not, and it didn't work for the reason that on my error consul of the Visual Studio Code, thanks any way for your help!

Hi Friend, What is the helpers directory?

You dont need to create anything, just install the packages and run. dont change anything. 

helpers.py is a module, not a directory.

@zimbabox okay, but your use of the code that @Hasan provided isn't correct and the pictures and detail you've given isn't enough to help you. So, please share a public link to your code if you want help. You can feel free to schedule a 1-on-1 with me if you wish using the calendar link in my signature.

Thanks for your follow up on my issue. The issue is fixed now and I am into a new issue now! I am trying to implement the tutorial  "LLM Generic Function" and the code is not generating any output for some reason, I think it's outdated.

import openai import nlpcloud import cohere """ LLMs: OpenAI NlpCloud Cohere You can add your own """ def llm_generate_text(prompt,service,model): if service == 'OpenAI': generated_text = openai_generate(prompt,model) elif service == 'NlpCloud': generated_text = nlp_cloud_generate(prompt,model) elif service == 'Cohere': generated_text = cohere_generate(prompt,model) return generated_text #Open AI Function openai.api_key = "sk-RNm6d9" def openai_generate(user_prompt,selected_model): completion = openai.chat.completions.create( model=selected_model, messages=[ {"role": "user", "content": user_prompt} ] ) return completion.choices[0].message.content #nlpCloud Function nlp_cloud_key = "bc1dc0031" def nlp_cloud_generate(user_prompt,selected_model): client = nlpcloud.Client(selected_model, nlp_cloud_key, gpu=True, lang="en") result = client.generation( user_prompt, min_length=0, max_length=100, length_no_input=True, remove_input=True, end_sequence=None, top_p=1, temperature=0.8, top_k=50, repetition_penalty=1, length_penalty=1, do_sample=True, early_stopping=False, num_beams=1, no_repeat_ngram_size=0, num_return_sequences=1, bad_words=None, remove_end_sequence=False ) return result["generated_text"] #Cohere API cohere_api_key = "KXSfvlpAXW" def cohere_generate(user_prompt,selected_model): co = cohere.Client(cohere_api_key) # This is your trial API key response = co.generate( model=selected_model, prompt=user_prompt, max_tokens=300, temperature=0.9, k=0, stop_sequences=[], return_likelihoods='NONE') return response.generations[0].text

Thanks for your follow up on my issue. The issue is fixed now and I am into a new issue now! I am trying to implement the tutorial  "LLM Generic Function" and the code is not generating any output for some reason, I think it's outdated.

https://github.com/almutabbil/LLM_Generic_Function/tree/main

@zimbabox trying to generate with OpenAI? or another API?

any errors?

@admin Yes Hasan it is only with OpenAI and I am getting this error:

@zimbabox if you add your app.py (or whatever you called it) file to the repository I can try to help debug it.

@zimbabox did you update OpenAI Package to the latest?

I am on the "Generate Ideas lesson"  and I am getting this error, why is that?: 

@zimbabox you've given "service" as the service which isn't expected so you get an exception.  If you review the code in llm.py you'll see the filter for the expected service, give the function one of those. While you're at it "command" probably isn't what you want either.

@zimbabox the service must be one of the defined ones in the function. please review the "llm_generate_text" function.

@admin So if one should be called service, what should I call then the other two? I couldn't find your original llm.py file to compare the code with mine!