openai-cookbook
openai-cookbook copied to clipboard
openai
Examples and guides for using the OpenAI API
Included [Parea AI](https://www.parea.ai) (previously, OptimusPrompt) as a tool under resources. It provides advanced auto-prompt engineering techniques, as well as allows testing and versioning of prompts. 
> Note: SQL generation use cases are high-risk in a production environment - models can be unreliable when generating consistent SQL syntax. A more reliable way to solve this problem...
# Pick a name for the new index index_name = 'wikipedia-articles' # Check whether the index with the same name already exists - if so, delete it if index_name in...
chat_response = chat_completion_request( conversation.conversation_history, functions=functions ) print(chat_response.json()) result is :{'error': {'message': "Invalid value for 'content': expected a string, got null.", 'type': 'invalid_request_error', 'param': 'messages.[1].content', 'code': None}}
**Identify the file to be fixed** [The name of the file containing the problem: How_to_count_tokens_with_tiktoken.ipynb](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) **Describe the problem** The problem is that the supplied example code for computing token counts...
I just fixed duplicate "basic". https://github.com/openai/openai-cookbook/blob/41a5d394ca355e276ba21290696116c33f55ad9f/apps/chatbot-kickstarter/README.md?plain=1#L3
Hi, I see there is a paper list about prompting. Would like to suggest the complexity-based prompting paper (https://arxiv.org/abs/2210.00720) where the basic idea is to use cases with more reasoning...
I'm working with this file/example - Embedding_Wikipedia_articles_for_search.ipynb CATEGORY_TITLE = "Category:2022 Winter Olympics" Is there any way to set it to all categories? I need to scrape our whole support wiki....
Added Humanloop as an example paid product that can help with building and evaluating LLM apps.
