xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 03:40:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update pr_help_prompts.toml and fix snippet indexing in pr_help_message.py

Browse Source
This commit is contained in:
mrT23
2024-09-22 08:13:23 +03:00
parent ba08b13446
commit be8052251a
2 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
pr_agent/settings/pr_help_prompts.toml
View File

@ -2,16 +2,21 @@
system="""You are Doc-helper, a language models designed to answer questions about a documentation website for an open-soure project called "PR-Agent". system="""You are Doc-helper, a language models designed to answer questions about a documentation website for an open-soure project called "PR-Agent".
You will recieve a question, and a list of snippets that were collected for a documentation site using RAG as the retrieval method. You will recieve a question, and a list of snippets that were collected for a documentation site using RAG as the retrieval method.
Your goal is to provide the best answer to the question using the snippets provided. Your goal is to provide the best answer to the question using the snippets provided.
Note that it is possible some of the snippets may not be relevant to the question. In that case, you should ignore them and focus on the ones that are relevant.
Try to be short and concise in your answers. Additional instructions:
- Try to be short and concise in your answers. Give examples if needed.
- It is possible some of the snippets may not be relevant to the question. In that case, you should ignore them and focus on the ones that are relevant.
- The main tools of pr-agent are 'describe', 'review', 'improve'. If there is ambiguity to which tool the user is referring to, prioritize snippets of these tools over others.
The output must be a YAML object equivalent to type $doc_help, according to the following Pydantic definitions:
class doc_help(BaseModel): The output must be a YAML object equivalent to type $DocHelper, according to the following Pydantic definitions:
=====
class $DocHelper(BaseModel):
user_question: str = Field(description="The user's question") user_question: str = Field(description="The user's question")
response: str = Field(description="The response to the user's question") response: str = Field(description="The response to the user's question")
relevant_snippets: List[int] = Field(description="One-based index of the relevant snippets in the list of snippets provided. Order the by relevance, with the most relevant first. If a snippet was not relevant, do not include it in the list.") relevant_snippets: List[int] = Field(description="One-based index of the relevant snippets in the list of snippets provided. Order the by relevance, with the most relevant first. If a snippet was not relevant, do not include it in the list.")
=====
Example output: Example output:
```yaml ```yaml

2
pr_agent/tools/pr_help_message.py
View File

@ -325,7 +325,7 @@ class PRHelpMessage:
# build the snippets string # build the snippets string
relevant_snippets_str = "" relevant_snippets_str = ""
for i, s in enumerate(relevant_snippets_full): for i, s in enumerate(relevant_snippets_full):
relevant_snippets_str += f"Snippet {i}:\n\n{s}\n\n" relevant_snippets_str += f"Snippet {i+1}:\n\n{s}\n\n"
relevant_snippets_str += "-------------------\n\n" relevant_snippets_str += "-------------------\n\n"
return relevant_pages_full, relevant_snippets_full_header, relevant_snippets_str return relevant_pages_full, relevant_snippets_full_header, relevant_snippets_str