Difference between revisions of "Retrieval Augmented Generation"
Jump to navigation
Jump to search
| Line 2: | Line 2: | ||
{{GlossaryEntry | {{GlossaryEntry | ||
| − | |description=Retrieval augmented generation (RAG) is a technique that grants generative artificial intelligence models information retrieval capabilities. It modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to augment information drawn from its own vast, static training data. This allows LLMs to use domain-specific and/or updated information. | + | |description=Retrieval augmented generation (RAG) is a technique that grants generative artificial intelligence models information retrieval capabilities. It modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to augment information drawn from its own vast, static training data. This allows LLMs to use domain-specific and/or updated information. Use cases include providing chatbot access to internal company data, or giving factual information only from an authoritative source. |
|references=https://en.wikipedia.org/wiki/Retrieval-augmented_generation | |references=https://en.wikipedia.org/wiki/Retrieval-augmented_generation | ||
|lang=en | |lang=en | ||
}} | }} | ||
| − | + | ||
= Links = | = Links = | ||
[https://weaviate.io/blog/introduction-to-rag?utm_source=newsletter.weaviate.io&utm_medium=referral&utm_campaign=introducing-european-hack-nights-compound-ai-systems-and-ai-in-education Weaviate blog entry on RAG] | [https://weaviate.io/blog/introduction-to-rag?utm_source=newsletter.weaviate.io&utm_medium=referral&utm_campaign=introducing-european-hack-nights-compound-ai-systems-and-ai-in-education Weaviate blog entry on RAG] | ||
Latest revision as of 16:03, 10 November 2024
GlossaryEntry
| GlossaryEntry | |
|---|---|
| responsible | |
| state | |
| since | |
| description | Retrieval augmented generation (RAG) is a technique that grants generative artificial intelligence models information retrieval capabilities. It modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to augment information drawn from its own vast, static training data. This allows LLMs to use domain-specific and/or updated information. Use cases include providing chatbot access to internal company data, or giving factual information only from an authoritative source. |
| references | https://en.wikipedia.org/wiki/Retrieval-augmented_generation |
| lang | en |
| master | |