370
edits
ChatGPT Plugins: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 4: | Line 4: | ||
==Browsing== | ==Browsing== | ||
{{see also|ChatGPT Browsing}} | |||
Influenced by prior projects like [[WebGPT]], [[GopherCite]], [[BlenderBot2]], [[LaMDA2]], and more, [[browsing-capable language models]] can retrieve information from the [[web]], broadening their knowledge beyond their training dataset. This enables ChatGPT to engage with current information and deliver more pertinent responses to user inquiries. | Influenced by prior projects like [[WebGPT]], [[GopherCite]], [[BlenderBot2]], [[LaMDA2]], and more, [[browsing-capable language models]] can retrieve information from the [[web]], broadening their knowledge beyond their training dataset. This enables ChatGPT to engage with current information and deliver more pertinent responses to user inquiries. | ||
==Code Interpreter== | ==Code Interpreter== | ||
{{see also|ChatGPT Code Interpreter}} | |||
The [[code interpreter]] supplies ChatGPT with a functional [[Python]] interpreter within a protected, firewalled execution environment, as well as temporary disk space. The interpreter plugin assesses code in a persistent session that remains active throughout a chat conversation. Users can upload files to the workspace and download their work results. | The [[code interpreter]] supplies ChatGPT with a functional [[Python]] interpreter within a protected, firewalled execution environment, as well as temporary disk space. The interpreter plugin assesses code in a persistent session that remains active throughout a chat conversation. Users can upload files to the workspace and download their work results. | ||
| Line 16: | Line 18: | ||
==Retrieval== | ==Retrieval== | ||
The open-source retrieval plugin ([https://github.com/openai/chatgpt-retrieval-plugin GitHub Link]) allows ChatGPT access private or organizational information sources, including files, notes, emails, or public documentation, upon user authorization. Users can acquire pertinent document excerpts from their data sources by posing questions or conveying requirements in [[natural language]]. | {{see also|ChatGPT Retrieval}} | ||
The open-source [[retrieval]] plugin ([https://github.com/openai/chatgpt-retrieval-plugin GitHub Link]) allows ChatGPT access private or organizational information sources, including files, notes, emails, or public documentation, upon user authorization. Users can acquire pertinent document excerpts from their data sources by posing questions or conveying requirements in [[natural language]]. | |||
Developers can deploy their own version of the plugin, which utilizes [[OpenAI embeddings]] and collaborates with an array of [[vector database]]s ([[Milvus]], [[Pinecone]], [[Qdrant]], [[Redis]], [[Weaviate]], or [[Zilliz]]) for [[document indexing]] and [[document searching|searching]]. Information sources can be synchronized with the database via webhooks. | Developers can deploy their own version of the plugin, which utilizes [[OpenAI embeddings]] and collaborates with an array of [[vector database]]s ([[Milvus]], [[Pinecone]], [[Qdrant]], [[Redis]], [[Weaviate]], or [[Zilliz]]) for [[document indexing]] and [[document searching|searching]]. Information sources can be synchronized with the database via webhooks. | ||