highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-07-12 14:12:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

Reworked chunking to support mega chunks (#2032)

Browse Source
This commit is contained in:
hagen-danswer
2024-08-14 22:18:53 -07:00
committed by GitHub
parent 680388537b
commit 61b5bd569b
27 changed files with 1522 additions and 1156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
backend/tests/regression/answer_quality/README.md
View File

@ -17,14 +17,17 @@ This Python script automates the process of running search quality tests for a b
1. Ensure you have the required dependencies installed.
2. Configure the `search_test_config.yaml` file based on the `search_test_config.yaml.template` file.
3. Configure the `.env_eval` file in `deployment/docker_compose` with the correct environment variables.
4. Navigate to Danswer repo:
4. Set up the PYTHONPATH permanently:
Add the following line to your shell configuration file (e.g., `~/.bashrc`, `~/.zshrc`, or `~/.bash_profile`):
```
export PYTHONPATH=$PYTHONPATH:/path/to/danswer/backend
```
Replace `/path/to/danswer` with the actual path to your Danswer repository.
After adding this line, restart your terminal or run `source ~/.bashrc` (or the appropriate config file) to apply the changes.
5. Navigate to Danswer repo:
```
cd path/to/danswer
```
5. Set Python Path variable:
```
export PYTHONPATH=$PYTHONPATH:$PWD/backend
```
6. Navigate to the answer_quality folder:
```
cd backend/tests/regression/answer_quality

1
backend/tests/regression/answer_quality/api_utils.py
View File

@ -66,7 +66,6 @@ def get_answer_from_query(
except Exception as e:
print("Failed to answer the questions:")
print(f"\t {str(e)}")
print("Try restarting vespa container and trying agian")
raise e
return context_data_list, answer

15
backend/tests/regression/answer_quality/file_uploader.py
View File

@ -52,6 +52,7 @@ def upload_test_files(zip_file_path: str, env_name: str) -> None:
def manage_file_upload(zip_file_path: str, env_name: str) -> None:
start_time = time.time()
unzipped_file_paths = unzip_and_get_file_paths(zip_file_path)
total_file_count = len(unzipped_file_paths)
problem_file_list: list[str] = []
@ -84,15 +85,17 @@ def manage_file_upload(zip_file_path: str, env_name: str) -> None:
time.sleep(10)
problem_file_csv_path = os.path.join(current_dir, "problem_files.csv")
with open(problem_file_csv_path, "w", newline="") as csvfile:
csvwriter = csv.writer(csvfile)
csvwriter.writerow(["Problematic File Paths"])
for problem_file in problem_file_list:
csvwriter.writerow([problem_file])
if problem_file_list:
problem_file_csv_path = os.path.join(current_dir, "problem_files.csv")
with open(problem_file_csv_path, "w", newline="") as csvfile:
csvwriter = csv.writer(csvfile)
csvwriter.writerow(["Problematic File Paths"])
for problem_file in problem_file_list:
csvwriter.writerow([problem_file])
for file in unzipped_file_paths:
os.unlink(file)
print(f"Total time taken: {(time.time() - start_time)/60} minutes")
if __name__ == "__main__":