|
| 1 | +""" |
| 2 | +This script syncs the Haystack docs HTML files to the deepset workspace for search indexing. |
| 3 | +
|
| 4 | +It is used in the docs_search_sync.yml workflow. |
| 5 | +
|
| 6 | +1. Collects all HTML files from the docs and reference directories for the stable Haystack version. |
| 7 | +2. Uploads the HTML files to the deepset workspace. |
| 8 | + - A timestamp-based metadata field is used to track document versions in the workspace. |
| 9 | +3. Deletes the old HTML files from the deepset workspace. |
| 10 | + - Since most files are overwritten during upload, only a small number of deletions is expected. |
| 11 | + - In case MAX_DELETIONS_SAFETY_LIMIT is exceeded, we block the deletion. |
| 12 | +""" |
| 13 | + |
| 14 | +import os |
| 15 | +import sys |
| 16 | +import time |
| 17 | +from pathlib import Path |
| 18 | + |
| 19 | +import requests |
| 20 | +from deepset_cloud_sdk.workflows.sync_client.files import DeepsetCloudFile, WriteMode, list_files, upload_texts |
| 21 | + |
| 22 | +DEEPSET_WORKSPACE_DOCS_SEARCH = os.environ["DEEPSET_WORKSPACE_DOCS_SEARCH"] |
| 23 | +DEEPSET_API_KEY_DOCS_SEARCH = os.environ["DEEPSET_API_KEY_DOCS_SEARCH"] |
| 24 | + |
| 25 | +# If there are more files to delete than this limit, it's likely that something went wrong in the upload process. |
| 26 | +MAX_DELETIONS_SAFETY_LIMIT = 20 |
| 27 | + |
| 28 | + |
| 29 | +def collect_docs_files(version: int) -> list[DeepsetCloudFile]: |
| 30 | + """ |
| 31 | + Collect all HTML files from the docs and reference directories. |
| 32 | +
|
| 33 | + Returns a list of DeepsetCloudFile objects. |
| 34 | + """ |
| 35 | + repo_root = Path(__file__).parent.parent.parent |
| 36 | + build_dir = repo_root / "docs-website" / "build" |
| 37 | + # we want to exclude previous and temporarily unstable versions (2.x) and next version (next) |
| 38 | + exclude = ("2.", "next") |
| 39 | + |
| 40 | + files = [] |
| 41 | + for section in ("docs", "reference"): |
| 42 | + for subfolder in (build_dir / section).iterdir(): |
| 43 | + if subfolder.is_dir() and not any(x in subfolder.name for x in exclude): |
| 44 | + for html_file in subfolder.rglob("*.html"): |
| 45 | + files.append( |
| 46 | + DeepsetCloudFile( |
| 47 | + # The build produces files like docs/agents/index.html or reference/agents-api/index.html. |
| 48 | + # For file names, we want to use the parent directory name (agents.html or agents-api.html) |
| 49 | + name=f"{html_file.parent.name}.html", |
| 50 | + text=html_file.read_text(), |
| 51 | + meta={ |
| 52 | + "type": "api-reference" if section == "reference" else "documentation", |
| 53 | + "version": version, |
| 54 | + }, |
| 55 | + ) |
| 56 | + ) |
| 57 | + return files |
| 58 | + |
| 59 | + |
| 60 | +def delete_files(file_names: list[str]) -> None: |
| 61 | + """ |
| 62 | + Delete files from the deepset workspace. |
| 63 | + """ |
| 64 | + url = f"https://api.cloud.deepset.ai/api/v1/workspaces/{DEEPSET_WORKSPACE_DOCS_SEARCH}/files" |
| 65 | + payload = {"names": file_names} |
| 66 | + headers = {"Accept": "application/json", "Authorization": f"Bearer {DEEPSET_API_KEY_DOCS_SEARCH}"} |
| 67 | + response = requests.delete(url, json=payload, headers=headers, timeout=300) |
| 68 | + response.raise_for_status() |
| 69 | + |
| 70 | + |
| 71 | +if __name__ == "__main__": |
| 72 | + version = time.time_ns() |
| 73 | + print(f"Docs version: {version}") |
| 74 | + |
| 75 | + print("Collecting docs files from build directory") |
| 76 | + dc_files = collect_docs_files(version) |
| 77 | + print(f"Collected {len(dc_files)} docs files") |
| 78 | + |
| 79 | + if len(dc_files) == 0: |
| 80 | + print("No docs files found. Something is wrong. Exiting.") |
| 81 | + sys.exit(1) |
| 82 | + |
| 83 | + print("Uploading docs files to deepset") |
| 84 | + summary = upload_texts( |
| 85 | + workspace_name=DEEPSET_WORKSPACE_DOCS_SEARCH, |
| 86 | + files=dc_files, |
| 87 | + api_key=DEEPSET_API_KEY_DOCS_SEARCH, |
| 88 | + blocking=True, # Very important to ensure that DC is up to date when we query for deletion |
| 89 | + timeout_s=300, |
| 90 | + show_progress=True, |
| 91 | + write_mode=WriteMode.OVERWRITE, |
| 92 | + enable_parallel_processing=True, |
| 93 | + ) |
| 94 | + print(f"Uploaded docs files to deepset\n{summary}") |
| 95 | + if summary.failed_upload_count > 0: |
| 96 | + print("Failed to upload some docs files. Stopping to prevent risky deletion of old files.") |
| 97 | + sys.exit(1) |
| 98 | + |
| 99 | + print("Listing old docs files from deepset") |
| 100 | + odata_filter = f"version lt '{version}'" |
| 101 | + old_files_names = [ |
| 102 | + f.name |
| 103 | + for batch in list_files( |
| 104 | + workspace_name=DEEPSET_WORKSPACE_DOCS_SEARCH, api_key=DEEPSET_API_KEY_DOCS_SEARCH, odata_filter=odata_filter |
| 105 | + ) |
| 106 | + for f in batch |
| 107 | + ] |
| 108 | + |
| 109 | + print(f"Found {len(old_files_names)} old files to delete") |
| 110 | + if len(old_files_names) > MAX_DELETIONS_SAFETY_LIMIT: |
| 111 | + print( |
| 112 | + f"Found >{MAX_DELETIONS_SAFETY_LIMIT} old files to delete. " |
| 113 | + "Stopping because something could have gone wrong in the upload process." |
| 114 | + ) |
| 115 | + sys.exit(1) |
| 116 | + |
| 117 | + if len(old_files_names) > 0: |
| 118 | + print("Deleting old docs files from deepset") |
| 119 | + delete_files(old_files_names) |
| 120 | + print("Deleted old docs files from deepset") |
0 commit comments