feat(#156): mcw col

h1alexbel · h1alexbel · commit a8685a97a54a · 2024-10-18T15:28:06.000+03:00
diff --git a/sr-data/src/sr_data/steps/embed.py b/sr-data/src/sr_data/steps/embed.py
@@ -44,7 +44,7 @@ def main(repos, prefix, hf, cohere):
     :param cohere Cohere token
     """
     frame = pd.read_csv(repos)
-    frame["top"] = frame["top"].apply(
+    frame["mcw"] = frame["mcw"].apply(
         lambda words:
         words.replace("[", "").replace("]", "").replace("'", "")
     )
@@ -69,7 +69,7 @@ def embed_cohere(key, texts, prefix):
     embeddings = pd.DataFrame(
         np.asarray(
             client.embed(
-                texts=texts["top"].tolist(), input_type="search_document", model="embed-english-v3.0"
+                texts=texts["mcw"].tolist(), input_type="search_document", model="embed-english-v3.0"
             ).embeddings
         )
     )

Original file line number	Diff line number	Diff line change
`@@ -44,7 +44,7 @@ def main(repos, prefix, hf, cohere):`
`44`	`44`	`:param cohere Cohere token`
`45`	`45`	`"""`
`46`	`46`	`frame = pd.read_csv(repos)`
`47`		`- frame["top"] = frame["top"].apply(`
	`47`	`+ frame["mcw"] = frame["mcw"].apply(`
`48`	`48`	`lambda words:`
`49`	`49`	`words.replace("[", "").replace("]", "").replace("'", "")`
`50`	`50`	`)`
`@@ -69,7 +69,7 @@ def embed_cohere(key, texts, prefix):`
`69`	`69`	`embeddings = pd.DataFrame(`
`70`	`70`	`np.asarray(`
`71`	`71`	`client.embed(`
`72`		`- texts=texts["top"].tolist(), input_type="search_document", model="embed-english-v3.0"`
	`72`	`+ texts=texts["mcw"].tolist(), input_type="search_document", model="embed-english-v3.0"`
`73`	`73`	`).embeddings`
`74`	`74`	`)`
`75`	`75`	`)`