diff options
Diffstat (limited to 'setup.py')
| -rw-r--r-- | setup.py | 35 |
1 files changed, 17 insertions, 18 deletions
@@ -146,21 +146,20 @@ def generate_summary(prompt): if (len(enc.encode(prompt)) > 3000): return "too long to summarize." - prompt = prompt + '\nSummarize the above code: ' - - # response = openai.ChatCompletion.create( - # model="gpt-3.5-turbo", - # messages=[{"role": "user", "content": prompt}], - # temperature=0.7, - # max_tokens=1024, - # top_p=1.0, - # frequency_penalty=0.0, - # presence_penalty=0.0, - # stop=["\"\"\""] - # ) - - #return response["choices"][0]["message"]["content"] - return 'herro. this is a test summary' + prompt = prompt + '\nSummarize the above code (be succinct): ' + + response = openai.ChatCompletion.create( + model="gpt-3.5-turbo", + messages=[{"role": "user", "content": prompt}], + temperature=0.7, + max_tokens=300, + top_p=1.0, + frequency_penalty=0.0, + presence_penalty=0.0, + stop=["\"\"\""] + ) + + return response["choices"][0]["message"]["content"] # create blob. the blob just contains the file path and the source code. def blobify(pandaSeries): @@ -234,9 +233,9 @@ def setup( print('generating embeddings') embedding_model = "text-embedding-ada-002" - #code_df["embedding_summary"] = code_df.summary.apply( - # [lambda x: get_embedding(x, engine=embedding_model)] - # ) + code_df["embedding_summary"] = code_df.summary.apply( + [lambda x: get_embedding(x, engine=embedding_model)] + ) print('done with embeddings') code_df.to_csv(output_csv_filepath) |