which api is best to get a custom gpt api that can answer employees questions about documents I upload to the bot. the bot shouldn't be able to do research of its own.
#custom assistant
tiny sedge
twilit siloBOT
Hi @tiny sedge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Based on the information provided in the extracts, you should consider using the Assistants API from OpenAI for your use case. Assistants are an API product for developers and can be used to create a custom GPT model that can answer questions about documents you upload to the bot.
However, it's important to note that the cost per query can be high and there are limitations such as maximum context length, iterative, and delayed output. You would also bear the cost if you make an API that costs you significant money for every use, such as fulfilling general user requests with AI model calls of your own [source] (https://community.openai.com/t/503940).
Custom GPTs are exclusive to the ChatGPT interface and are not practical for backend API use. They are only available via ChatGPT Plus and you can't connect to them as if they are a backend API [source] (https://community.openai.com/t/601866), [source] (https://community.openai.com/t/589655), [source] (https://community.openai.com/t/589868).
To create an Assistant, you can use the OpenAI Playground or directly in the API endpoint. Here is the documentation for the Assistants: **https://platform.openai.com/docs/assistants/overview** (https://platform.openai.com/docs/assistants/overview) and here is the API reference for the Assistants endpoint: **https://platform.openai.com/docs/api-reference/assistants** (https://platform.openai.com/docs/api-reference/assistants) [source] (https://community.openai.com/t/534153).
Please note that the bot will not be able to do research on its own as it will only be able to answer questions based on the documents and information you provide to it.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
tiny sedge
@twilit silo whats the pricing for 1 sentence message
twilit siloBOT
Let me check the knowledge base for you. One moment! :books:
The pricing for using OpenAI's models is based on the number of tokens processed, not the number of sentences. A token is roughly equivalent to 0.75 words. The cost per token varies depending on the specific model you are using.
For example, for GPT-4 models with 128k context lengths (e.g. gpt-4-1106-preview and gpt-4-1106-vision-preview), the price is $0.01 per 1k prompt tokens and $0.03 per 1k sampled tokens. For models with 8k context lengths (e.g. gpt-4 and gpt-4-0314), the price is $0.03 per 1k prompt tokens and $0.06 per 1k sampled tokens. For models with 32k context lengths (e.g. gpt-4-32k and gpt-4-32k-0314), the price is $0.06 per 1k prompt tokens and $0.12 per 1k sampled tokens [source] (https://help.openai.com/en/articles/7127956-how-much-does-gpt-4-cost).
For GPT-3.5-turbo-1106, the cost is $0.0010 per 1K tokens for input and $0.0020 per 1K tokens for output. For GPT-3.5-turbo, the cost is $0.0015 per 1K tokens for input and $0.0020 per 1K tokens for output [source] (https://community.openai.com/t/548748).