navan
/
FlixRec
mirror of https://github.com/navanchauhan/FlixRec.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

fixed code for pushing to pinecone

This commit is contained in:
navanchauhan 2022-05-21 11:11:59 -06:00
parent 4b78fbe5e6
commit 34965e2cdb
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
db2pc.py
View File

@ -22,7 +22,7 @@ batch_size = 32
df = pd.read_sql("Select * from movies", engine) df = pd.read_sql("Select * from movies", engine)
df["combined_text"] = df["title"] + ": " + df["overview"].fillna('') + " - " + df["tagline"].fillna('') + " Genres:- " + df["genres"].fillna('') df["combined_text"] = df["title"] + ": " + df["overview"].fillna('') + " - " + df["tagline"].fillna('') + " Genres:- " + df["genres"].fillna('')
print(len(df["combined_text"].tolist())) print(f'Length of Combined Text: {len(df["combined_text"].tolist())}')
for x in tqdm(range(0,len(df),batch_size)): for x in tqdm(range(0,len(df),batch_size)):
to_send = [] to_send = []
@ -31,7 +31,7 @@ for x in tqdm(range(0,len(df),batch_size)):
embeddings = model.encode(sentences) embeddings = model.encode(sentences)
for idx, value in enumerate(trakt_ids): for idx, value in enumerate(trakt_ids):
to_send.append( to_send.append(
{ (
value: embeddings[idx].tolist() str(value), embeddings[idx].tolist()
}) ))
index.upsert(to_send) index.upsert(to_send)