Stack Overflow
Stack Overflow

Questions tagged [gpt-3]

Use this tag with Generative Pre-trained Transformer 3 (GPT-3). Do not use with GPT-2 or the ad tagging library (GPT).

References:

GPT-3 (Wikipedia)

Related tags:

296 questions
3
votes
2 answers

How to ping the ChatGPT via curl and retain the state of conversation

The code below is working. I can curl questions to ChatGPT and it replies on a one-off basis. However, if I try to engage in a conversation that require the state of the previous submissions to be referenced, the chat can not follow. I would like to…
William
  • 4,422
  • 17
  • 55
  • 108
3
votes
2 answers

OpenAI GPT-3 API error: "TypeError: openai.completions is not a function"

I am trying to run the test code in the tutorial https://harishgarg.com/writing/building-a-chat-app-with-gpt-3-reactjs-and-nextjs-a-step-by-step-guide/ and I get TypeError: openai.completions is not a function from the following code I put in…
Dave Nixon
  • 101
  • 1
  • 5
3
votes
0 answers

Problems getting GPT-3 to conduct statistical analysis of a dataframe or json file

I'm having problems getting gpt-3 to do simple statistical summaries of a dataframe/json file - using python pandas as the suggested prompt, oddly it does categorical analysis of the df, ie value_counts etc but seems to hallucinate when faced with…
Weegie
  • 31
  • 2
3
votes
2 answers

How to solve API connection error and SSL certification error while connecting to GPT-3 open AI?

I am trying to run a python script(jupyter notebook) by experimenting with GPT-3 open AI to create some NLP project and understand its functions and used cases. I got an error of SSL certification and API connection while I was trying to open a JSON…
pewdpy
  • 31
  • 1
  • 1
  • 4
3
votes
1 answer

GPT-3 completions not working with API KEY

Sorry if this is a simple problem but I'm new to this stuff. İ have my code below, but the API returns saying İ don't have the right API key put it. const { Configuration, OpenAIApi } = require("openai"); const configuration = new Configuration({ …
Adam Zaidi
  • 51
  • 3
3
votes
1 answer

OpenAI API repeats completions with no variation

I have tried implementing a chatbot in OpenAI with Javascript, using the official OpenAI npm dependency. The way i have solved it, is that i have an array of chat messages, that gets joined by newlines, and sent as the prompt to the…
Adrian Andersen
  • 83
  • 2
  • 6
3
votes
2 answers

Structuring dataset for OpenAI's GPT-3 fine tuning

The fine tuning endpoint for OpenAI's API seems to be fairly new, and I can't find many examples of fine tuning datasets online. I'm in charge of a voicebot, and I'm testing out the performance of GPT-3 for general open-conversation questions. I'd…
fcagnola
  • 640
  • 7
  • 17
3
votes
1 answer

How to use files in the Answer api of OpenAI

As finally OpenAI opened the GPT-3 related API publicly, I am playing with it to explore and discover his potential. I am trying the Answer API, the simple example that is in the documentation: https://beta.openai.com/docs/guides/answers I upload…
btbbass
  • 125
  • 1
  • 9
2
votes
1 answer

How to make OpenAI stop prepending "A:" or "Answer:" to its answers?

Sometimes, my OpenAI API on call like const completion = await openai.createChatCompletion({ model: 'gpt-3.5-turbo', messages: [ { role: 'system', content: `You are ChatbotAssistant, an automated service to answer questions of…
Gishas
  • 380
  • 6
  • 21
2
votes
1 answer

OpenAI Function Calling Error ---- openai.error.InvalidRequestError:

I am creating a chatbot which can query all 'Views' in my database based on user query. I tried many other methods but didn't succeed so now I thought I should try OpenAI's function calling. What I did: I created a function for one of the view. In…
naam_nrj
  • 33
  • 6
2
votes
2 answers

how to use tiktoken in offline mode computer

import tiktoken tokenizer = tiktoken.get_encoding("cl100k_base") tokenizer = tiktoken.encoding_for_model("gpt-3.5-turbo") text = "Hello, nice to meet you" tokenizer.encode(text) This keeps showing error called requests.exceptions.SSLError.…
SiSi
  • 51
  • 1
  • 4
2
votes
1 answer

How to stop GPT-3.5-Turbo model from generating text (azure)?

In my use case I am using openai models hosted on azure. I am trying to generate a list of senteces or words with a specific length. Lets take this prompt as an example: Give 10 Examples of pizza ingredients: 1. tomatoes 2. mushrooms The…
dude
  • 79
  • 6
2
votes
1 answer

How can I train GPT-3 with my own company data using OpenAI's API?

I want to train GPT-3 with my company's data to perform specific NLP tasks using OpenAI's API. How can I train the GPT-3 model with my own data? What kind of data preprocessing do I need to perform before training the model? Are there any Python…
jazz
  • 31
  • 6
2
votes
1 answer

Error: PineconeClient: Project name not set, v0.0.10

Downloaded GitHub - mayooear/gpt4-pdf-chatbot-langchain: GPT4 & LangChain Chatbot for large PDF docs When I try to run the app, I get following error PineconeClient: Error getting project name: TypeError: fetch failed error - [Error:…
Rohit
  • 6,941
  • 17
  • 58
  • 102
2
votes
2 answers

Alpaca Large Language Model from Python script

I was able to install Alpaca under Linux and start and use it interactivelly via the corresponding ./chat command. However, I would like to run it not in interactive mode but from a Python (Jupyter) script with the prompt as string parameter. Also,…
DJRDS
  • 27
  • 5
1 2 3
…
19 20