#knowledge cap
1 messages · Page 1 of 1 (latest)
Hi @shadow cloak. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
When creating a custom GPT and utilizing the "knowledge" section, there are indeed specific caps or limits on how many documents you can upload and the amount of information each can contain. Based on the information provided:
- You can attach up to 20 files to a GPT.
- Each file can be up to 512 MB in size.
- Each file can contain up to 2,000,000 tokens.
It's important to note that while files containing images can be included, only the text within these files is currently processed. The GPT breaks the text up into chunks, creates embeddings of these chunks, and stores them for later use. This process allows the GPT to access the uploaded files for additional context to augment user queries.
For more detailed guidance on managing files and understanding the limitations, you might find the documentation on Knowledge in GPTs (https://help.openai.com/en/articles/8843948-knowledge-in-gpts) helpful.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@shadow cloak kapa.ai is still learning and improving, please let us know how it did by reacting below
@hoary oxide if you upload more documents into the knowledge section does it take longer to search through it?
Let me check the knowledge base for you. One moment! :books:
Based on the extracts provided, there is no direct information regarding whether uploading more documents into the "knowledge" section directly impacts the search time or performance. The extracts discuss the capabilities and limits related to the number of documents, file size, and token count but do not explicitly address the relationship between the quantity of uploaded documents and the time it takes for the GPT to search through this knowledge.
For specific details on performance implications or optimization tips related to the "knowledge" feature, it would be advisable to consult the official OpenAI documentation or reach out to OpenAI support for more targeted guidance.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@shadow cloak kapa.ai is still learning and improving, please let us know how it did by reacting below
@hoary oxide one last question. can the AI open links in the documents uploaded to “knowledge”?
Let me check the knowledge base for you. One moment! :books:
Based on the information provided in the extracts, when documents are uploaded to the "knowledge" section for use with a GPT, only the text within these documents is processed. There is no mention of the AI's ability to actively open links contained within the documents. The focus is on breaking the text up into chunks, creating embeddings, and storing them for later use to augment user queries with additional context. This implies that the AI treats the content of the documents, including any links, as text data rather than interactive elements it can engage with directly.