Questions tagged [chatgpt-api]

Use for questions about the OpenAI ChatGPT (i.e., GPT-3.5) API. Do not use it for questions about any other OpenAI API (GPT-3, GPT-4, etc.).

377 questions
1
vote
1 answer

Summarizer PDF with langchain isn't working when run on multiple PDFs at once

when I use the following code - which summarizes long PDFs -, it works fine for the first PDF. But if I use it for a second PDF (that is, I change the file path to another PDF), it still puts out the summary for the first PDF, as if the embeddings…
1
vote
0 answers

PowerBI Custom Visual with ChatGPT

I am developing a custom visual into Power BI using TypeScript. I have an input of type text for user input prompt and an input of type text for ChatGPT answer. The idea is that the user can ask anything about report's data or any report's visual…
1
vote
1 answer

How to seperate data for multiple chatbots in pinecone vector database service?

I am building a platform where users can upload their custom data, and build a chatbot. I am thinking of using lanchain + open ai embeddings + chat gpt api + pinecone to manage this service. I was checking out pinecone documentation at…
1
vote
0 answers

ModuleNotFoundError: No module named 'llama_index.langchain_helpers.chatgpt'

I'd like to use ChatGPTLLMPredictor from llama_index.langchain_helpers.chatgpt, but I got an error below on M1 Macbook Air. ModuleNotFoundError: No module named 'llama_index.langchain_helpers.chatgpt' My code looks like this and line 3 is the…
Taishi Kato
  • 370
  • 1
  • 3
  • 11
1
vote
0 answers

Unable to use Llama Index with AWS Lambda

I am using Llama Index to create a custom bot using AWS Lambda, but when I try to create its layer and upload it to the AWS layer, I am getting "package not found" errors for different libraries. I tried to delete some packages from the Llama Index…
1
vote
2 answers

Valid characters for ChatGPT prompt?

With following request payload (generated from JSON.stringify(data) without error): { "model": "gpt-3.5-turbo", "messages": [ { "role": "user", "content": "convert 4000 m² into acres." } ] } I got following ChatGPT API error…
ubertao
  • 229
  • 1
  • 2
  • 12
1
vote
1 answer

ChatGPT completion /v1/chat/completions memorize across multiple requests

When I use user parameter on https://api.openai.com/v1/chat/completions, the memory is not persisted across multiple requests. How can we let the model memorize it across multiple requests? Eg. is the message "My name is XXX" remembered by the…
angelokh
  • 9,426
  • 9
  • 69
  • 139
1
vote
0 answers

How to parse the OpenAIStream so there are no spaces and lists are correctly formatted?

I have the OpenAI's API set to stream the response and it's working! The problem is the results have extra spaces and my formatting is not working to eliminate the spacing issue nor is it parsing the lists. Here's the code. How to correctly parse…
1
vote
1 answer

OpenAI ChatGPT (GPT-3.5) API: Can I use a fine-tuned GPT-3 model with the GPT-3.5 API endpoint (error: "Invalid URL (POST /v1/chat/completions)")?

After we create a fine-tuned model, how can we use it at /v1/chat/completions? We tried this but it gave an error curl --location 'https://api.openai.com/v1/chat/completions' \ --header 'Authorization: Bearer TOKEN' \ --header 'Content-Type:…
angelokh
  • 9,426
  • 9
  • 69
  • 139
1
vote
0 answers

Cannot get the API REST result using Retrofit

I've been searching a long time, but I didn't find anything that could help me. I'm trying to use a OpenAI API, but every time I'm getting errors. What I am doing wrong? The error is: The code is: RetrofitInstance class RetrofitInstance { …
1
vote
1 answer

How Do I Set Up LLMPredictor To Be able To Create Indexes?

I am following along with this video video making a ChatGPT bot. Everything was fine until I the very end where I am trying to create the model and indexes for the bot. I copied the code directly from the video creator's notebook ` def…
JedM1
  • 11
  • 2
1
vote
0 answers

word to word gpt api responce stream in react native

Is there a way to implement GPT API with word to word api I already try implement in javascript directly into app but its not working I want to use Chat GPT Turbo api directly in react native (expo) with word by word stream here is working example…
1
vote
0 answers

Give GPT (with own knowledge base) an instruction on how to behave before user prompt

I have given GPT some information in CSV format to learn and now I would like to transmit an instruction on how to behave before the user prompt. def chatbot(input_text): index = GPTSimpleVectorIndex.load_from_disk('index.json') …
Bill Bronson
  • 530
  • 2
  • 9
  • 24
1
vote
1 answer

Can I use a single ChatGPT-3 API key for multiple projects simultaneously?

I am a noobie programmer in college and I am trying to learn how to use API keys. I am currently using the ChatGPT-3 API for my Siri personal assistant project, and it's been working well for me so far. Now, I am developing another application - a…
PartiMarti
  • 21
  • 5
1
vote
1 answer

How can I stream using ChatGPT with Delphi?

I am playing around with ChatGPT and Delphi, using the OpenAI library at: https://github.com/HemulGM/DelphiOpenAI. It supports streaming, but I can't figure out the ChatGPT mechanism for streaming. I can create a Chat, and get all data back in one…
user1009073
  • 3,160
  • 7
  • 40
  • 82