Archives/openai-cookbook
2
0
Fork 0
mirror of https://github.com/openai/openai-cookbook synced 2024-11-13 07:10:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix broken relative links in Question answering using embeddings (#796)

Browse Source
This commit is contained in:
pavlovp 2023-10-19 01:09:53 +02:00 committed by GitHub
parent 85124ea987
commit 8ea904faa8
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
articles/text_comparison_examples.md
View File

@ -28,19 +28,19 @@ The simplest way to use embeddings for search is as follows:
* Find the closest embeddings in your database
* Return the top results
An example of how to use embeddings for search is shown in [Semantic_text_search_using_embeddings.ipynb](examples/Semantic_text_search_using_embeddings.ipynb).
An example of how to use embeddings for search is shown in [Semantic_text_search_using_embeddings.ipynb](../examples/Semantic_text_search_using_embeddings.ipynb).
In more advanced search systems, the cosine similarity of embeddings can be used as one feature among many in ranking search results.
## Question answering
The best way to get reliably honest answers from GPT-3 is to give it source documents in which it can locate correct answers. Using the semantic search procedure above, you can cheaply search through a corpus of documents for relevant information and then give that information to GPT-3 via the prompt to answer a question. We demonstrate this in [Question_answering_using_embeddings.ipynb](examples/Question_answering_using_embeddings.ipynb).
The best way to get reliably honest answers from GPT-3 is to give it source documents in which it can locate correct answers. Using the semantic search procedure above, you can cheaply search through a corpus of documents for relevant information and then give that information to GPT-3 via the prompt to answer a question. We demonstrate this in [Question_answering_using_embeddings.ipynb](../examples/Question_answering_using_embeddings.ipynb).
## Recommendations
Recommendations are quite similar to search, except that instead of a free-form text query, the inputs are items in a set.
An example of how to use embeddings for recommendations is shown in [Recommendation_using_embeddings.ipynb](examples/Recommendation_using_embeddings.ipynb).
An example of how to use embeddings for recommendations is shown in [Recommendation_using_embeddings.ipynb](../examples/Recommendation_using_embeddings.ipynb).
Similar to search, these cosine similarity scores can either be used on their own to rank items or as features in larger ranking algorithms.
@ -48,4 +48,4 @@ Similar to search, these cosine similarity scores can either be used on their ow
Although OpenAI's embedding model weights cannot be fine-tuned, you can nevertheless use training data to customize embeddings to your application.
In [Customizing_embeddings.ipynb](examples/Customizing_embeddings.ipynb), we provide an example method for customizing your embeddings using training data. The idea of the method is to train a custom matrix to multiply embedding vectors by in order to get new customized embeddings. With good training data, this custom matrix will help emphasize the features relevant to your training labels. You can equivalently consider the matrix multiplication as (a) a modification of the embeddings or (b) a modification of the distance function used to measure the distances between embeddings.
In [Customizing_embeddings.ipynb](../examples/Customizing_embeddings.ipynb), we provide an example method for customizing your embeddings using training data. The idea of the method is to train a custom matrix to multiply embedding vectors by in order to get new customized embeddings. With good training data, this custom matrix will help emphasize the features relevant to your training labels. You can equivalently consider the matrix multiplication as (a) a modification of the embeddings or (b) a modification of the distance function used to measure the distances between embeddings.