Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added a more optimal claude prompt #184

Merged
merged 2 commits into from
Jun 26, 2024
Merged

Added a more optimal claude prompt #184

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
68686d1
updated claude prompt to make it optimal
rishsriv Jun 26, 2024
7ec90ce
deleted unneded file
rishsriv Jun 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 5 additions & 8 deletions prompts/prompt_anthropic.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,9 @@
### Instructions:
Your task is to convert a text question to a SQL query that runs on Postgres, given a database schema. Return the SQL as a markdown string, nothing else.
Your task is to convert a text question to a PostgreSQL query, given a database schema.

### Input:
Generate a SQL query that answers the question `{user_question}`.
The question that you must generate a SQL for is this `{user_question}`.
{instructions}{glossary}
This query will run on a database whose schema is represented in this string:
This query will run on a database with the following schema:
{table_metadata_string}
{k_shot_prompt}
### Response:
{cot_instructions}Given the database schema, here is the SQL query that answers `{user_question}`:
```sql

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ooh anthropic performs better without cot?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yup slightly worse – which makes sense I guess! Larger model = more attention heads = better ability to pay attention to DDLs!

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ahh yes makes sense when you explain it

Just return the SQL query, nothing else.
6 changes: 1 addition & 5 deletions query_generators/anthropic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,11 +48,7 @@ def get_completion(
):
"""Get Anthropic chat completion for a given prompt and model"""
generated_text = ""
sys_prompt = prompt.split("### Input:")[0]
user_prompt = prompt.split("### Input:")[1].split("### Response:")[0]
messages = [
{"role": "user", "content": [{"type": "text", "text": user_prompt}]}
]
messages = [{"role": "user", "content": [{"type": "text", "text": prompt}]}]
try:
completion = anthropic.messages.create(
model=model,
Expand Down
Loading