Using Cohere and Pinecone to generate and index high-quality vector embeddings
trec
contains two label features and the text feature. Pass the questions from the text feature to Cohere to create embeddings.
1024
embedding dimensionality produced by Cohere’s embed-english-v3.0
model, and the 1000
samples you built embeddings for.
cohere-pinecone-trec
for storing the embeddings. When creating the index, you specify that you would like to use the cosine similarity metric to align with Cohere’s embeddings, and also pass the embedding dimensionality of 1024
.
index.describe_index_stats
that you have a 1024-dimensionality index populated with 1000 embeddings. Note that serverless indexes scale automatically as needed, so the index_fullness
metric is relevant only for pod-based indexes.
metadata
field. Let’s print out the top_k
most similar questions and their respective similarity scores.