From ad9ebbe7c78c2cf7c717d7898534371d59f325d9 Mon Sep 17 00:00:00 2001
From: Nate Buttke <nate-web@riseup.net>
Date: Wed, 26 Jul 2023 23:40:32 -0700
Subject: today's work. fixed multi-file parsing. don't send too-large files up
 to API. Generate embeddings.

---
 setup_cont.py | 16 ----------------
 1 file changed, 16 deletions(-)
 delete mode 100644 setup_cont.py

(limited to 'setup_cont.py')

diff --git a/setup_cont.py b/setup_cont.py
deleted file mode 100644
index 360c9f9..0000000
--- a/setup_cont.py
+++ /dev/null
@@ -1,16 +0,0 @@
-import ast
-from collections import defaultdict
-import os
-import pandas as pd
-import openai 
-import tiktoken
-from openai.embeddings_utils import get_embedding, cosine_similarity
-
-openai.api_key = os.getenv('END_OF_WORLD')
-
-df=pd.read_csv("setup_dataWithSummary.csv")
-embedding_model = "text-embedding-ada-002"
-df["embedding_summary"] = df.summary.apply([lambda x: get_embedding(x, engine=embedding_model)])
-print(df)
-
-df.to_csv('setup_dataWithSummaryEmbed.csv')
-- 
cgit v1.2.3