feat(api): add createEmbeddingForPart function #1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit adds a new function `createEmbeddingForPart` to the chat API route. This function takes a part and creates an embedding using the OpenAI API. The result is an array of numbers. The function is used to calculate the cosine similarity between the user's input and various parts of a mecha. The cosineSimilarity function has been added as well to calculate the cosine similarity between two arrays of numbers. The function checks if the lengths of the arrays are equal and appends zeros to the shorter array if needed. Then it calculates the dot product and norms of the arrays to determine the similarity. The POST handler in the chat API route has been updated to use the new functions. It creates an embedding for the user's input and calculates the cosine similarity between the user's input and various parts of the mecha. It then selects the top 5 parts with the highest similarity scores and includes them in the response to the user. In the page component, a new import statement has been added to import the `parts` module from the DB.
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
- The OpenAI model used for creating embeddings has been updated to 'text-embedding-ada-002'. This change ensures compatibility with the latest version of the model. - Additionally, in the cosineSimilarity function, added a check to return 0 if either vector is not defined to denote no similarity.
- Updated import statement to include CreateEmbeddingResponse type - Modified return type of createEmbeddingForPart function - Renamed variables for clarity - Modified cosineSimilarity function to accept and compare user embedding - Updated variable names in POST function for consistency - Updated cosineSimilarity function call in POST function to use userEmbedding - Added console log statement to debug userEmbedding
…part embeddings - Refactored the cosineSimilarity function to remove unnecessary conditional checks. - Added console logs to print the user and part embeddings for debugging purposes. These changes aim to improve code readability and aid in debugging any issues related to the embeddings.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit adds a new function
createEmbeddingForPartto the chat API route. This function takes a part and creates an embedding using the OpenAI API. The result is an array of numbers. The function is used to calculate the cosine similarity between the user's input and various parts of a mecha.The cosineSimilarity function has been added as well to calculate the cosine similarity between two arrays of numbers. The function checks if the lengths of the arrays are equal and appends zeros to the shorter array if needed. Then it calculates the dot product and norms of the arrays to determine the similarity.
The POST handler in the chat API route has been updated to use the new functions. It creates an embedding for the user's input and calculates the cosine similarity between the user's input and various parts of the mecha. It then selects the top 5 parts with the highest similarity scores and includes them in the response to the user.
In the page component, a new import statement has been added to import the
partsmodule from the DB.