xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-05 13:20:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

stable

Browse Source
This commit is contained in:
mrT23
2023-09-06 09:43:23 +03:00
parent bc95cf5b8e
commit 8962c9cf8a
2 changed files with 24 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pr_agent/settings/configuration.toml
View File

@ -100,7 +100,7 @@ polling_interval_seconds = 30
[pr_similar_issue] [pr_similar_issue]
skip_comments = false skip_comments = false
force_update_dataset = false force_update_dataset = false
max_issues_to_scan = 1000 max_issues_to_scan = 500
[pinecone] [pinecone]
# fill and place in .secrets.toml # fill and place in .secrets.toml

42
pr_agent/tools/pr_similar_issue.py
View File

@ -176,24 +176,24 @@ class PRSimilarIssue:
level=IssueLevel.ISSUE) level=IssueLevel.ISSUE)
) )
corpus.append(issue_record) corpus.append(issue_record)
if comments: if comments:
for j, comment in enumerate(comments): for j, comment in enumerate(comments):
comment_body = comment.body comment_body = comment.body
num_words_comment = len(comment_body.split()) num_words_comment = len(comment_body.split())
if num_words_comment < 10 or not isinstance(comment_body, str): if num_words_comment < 10 or not isinstance(comment_body, str):
continue continue
if len(issue_str) < 8000 or \ if len(comment_body) < 8000 or \
self.token_handler.count_tokens(comment_body) < MAX_TOKENS[MODEL]: self.token_handler.count_tokens(comment_body) < MAX_TOKENS[MODEL]:
comment_record = Record( comment_record = Record(
id=issue_key + ".comment_" + str(j + 1), id=issue_key + ".comment_" + str(j + 1),
text=comment_body, text=comment_body,
metadata=Metadata(repo=repo_name_for_index, metadata=Metadata(repo=repo_name_for_index,
username=username, # use issue username for all comments username=username, # use issue username for all comments
created_at=created_at, created_at=created_at,
level=IssueLevel.COMMENT) level=IssueLevel.COMMENT)
) )
corpus.append(comment_record) corpus.append(comment_record)
df = pd.DataFrame(corpus.dict()["documents"]) df = pd.DataFrame(corpus.dict()["documents"])
logging.info('Done') logging.info('Done')
@ -205,9 +205,13 @@ class PRSimilarIssue:
embeds = [record['embedding'] for record in res['data']] embeds = [record['embedding'] for record in res['data']]
except: except:
embeds = [] embeds = []
logging.error('Failed to embed entire list, embedding one by one...')
for i, text in enumerate(list_to_encode): for i, text in enumerate(list_to_encode):
res = openai.Embedding.create(input=[text], engine=MODEL) try:
embeds.append(res['data'][0]['embedding']) res = openai.Embedding.create(input=[text], engine=MODEL)
embeds.append(res['data'][0]['embedding'])
except:
embeds.append([0] * 1536)
df["values"] = embeds df["values"] = embeds
meta = DatasetMetadata.empty() meta = DatasetMetadata.empty()
meta.dense_model.dimension = len(embeds[0]) meta.dense_model.dimension = len(embeds[0])