Create embedding_generation.py

embedding_generation.py

@@ -0,0 +1,12 @@
+import pandas as pd
+import get_embedding from openai_api
+
+def compute_doc_embeddings(df: pd.DataFrame) -> dict[tuple[str, str], list[float]]:
+    """
+    Create an embedding for each row in the dataframe using the OpenAI Embeddings API.
+    
+    Return a dictionary that maps between each embedding vector and the index of the row that it corresponds to.
+    """
+    return {
+        idx: get_embedding(r.description) for idx, r in df.iterrows()
+    }