Support custom models #81
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…c, ollama with codellama)
Contributor
There was a problem hiding this comment.
Copilot reviewed 6 out of 20 changed files in this pull request and generated 1 comment.
Files not reviewed (14)
- api-keys.env.template: Language not supported
- py-src/data_formulator/agents/agent_utils.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_rec.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_clean.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_generic_py_concept.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_filter.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_sort_data.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_concept_derive.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_py_concept_derive.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_transformation.py: Evaluated as low risk
- src/views/EncodingShelfThread.tsx: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_load.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_code_explanation.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_transform_v2.py: Evaluated as low risk
Comments suppressed due to low confidence (3)
py-src/data_formulator/app.py:38
- [nitpick] The class name 'Client' is too generic and could lead to confusion. It should be renamed to something more specific like 'LiteLLMClient'.
from data_formulator.agents.client_utils import Client
py-src/data_formulator/app.py:132
- The function 'check_available_models' does not have any associated tests to verify its behavior. This function is critical as it checks the availability of models and should be covered by tests to ensure it works correctly under different scenarios.
@app.route('/check-available-models', methods=['GET', 'POST'])
src/app/dfSlice.tsx:695
- The
domainvariable is assigneduniqueValues, but the comment suggests it should beArray.from(columnValues). Confirm if the intended behavior is to use unique values or all column values.
const domain = uniqueValues; //Array.from(columnValues);
| app = Flask(__name__, static_url_path='', static_folder=os.path.join(APP_ROOT, "dist")) | ||
| CORS(app) | ||
|
|
||
| def get_client(model_config): |
There was a problem hiding this comment.
The 'html.escape' function is used to escape all values in 'model_config', which might not be necessary or appropriate for all fields (e.g., 'api_key'). This could lead to unintended behavior if the API key or other fields contain characters that are escaped.
Contributor
There was a problem hiding this comment.
Copilot reviewed 11 out of 26 changed files in this pull request and generated 3 comments.
Files not reviewed (15)
- api-keys.env.template: Language not supported
- py-src/data_formulator/agents/agent_utils.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_clean.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_generic_py_concept.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_py_concept_derive.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_filter.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_concept_derive.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_sort_data.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_load.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_transformation.py: Evaluated as low risk
- py-src/data_formulator/agents/agent_code_explanation.py: Evaluated as low risk
- src/views/EncodingBox.tsx: Evaluated as low risk
- src/views/DataFormulator.tsx: Evaluated as low risk
- src/app/dfSlice.tsx: Evaluated as low risk
- py-src/data_formulator/agents/agent_data_rec.py: Evaluated as low risk
Comments suppressed due to low confidence (1)
py-src/data_formulator/app.py:55
- The function should have test coverage to ensure that it correctly handles different model configurations and creates the Client instance with the appropriate parameters.
def get_client(model_config):
Comment on lines
210
to
212
| print("\n=== Data transformation result ===>\n") | ||
| print(choice.message.content + "\n") | ||
|
|
There was a problem hiding this comment.
Replace print statements with proper logging.
Suggested change
| print("\n=== Data transformation result ===>\n") | |
| print(choice.message.content + "\n") | |
| logger.info("\n=== Data transformation result ===>\n") | |
| logger.info(choice.message.content + "\n") |
Comment on lines
221
to
223
| print("\n=== Code blocks ===>\n") | ||
| print(code_blocks) | ||
|
|
There was a problem hiding this comment.
Replace print statements with proper logging.
Suggested change
| print("\n=== Code blocks ===>\n") | |
| print(code_blocks) | |
| logger.info("\n=== Code blocks ===>\n") | |
| logger.info(code_blocks) |
Comment on lines
249
to
251
| print("\n=== Candidates ===>\n") | ||
| print(candidates) | ||
|
|
There was a problem hiding this comment.
Replace print statements with proper logging.
Suggested change
| print("\n=== Candidates ===>\n") | |
| print(candidates) | |
| logger.info("\n=== Candidates ===>\n") | |
| logger.info(candidates) |
This was referenced Feb 12, 2025
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support running models beyond open ai models
api-keys.env, checkout https://github.com/microsoft/data-formulator/blob/dev/api-keys.env.template. Data Formulator will test and load them into the tool on start.