yujunjun/graphrag-accelerator
1
0
Fork 0
mirror of https://github.com/Azure-Samples/graphrag-accelerator.git synced 2025-06-27 04:39:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Quickstart notebook with API changes introduced in 83316b2 (#239)

Browse Source
This commit is contained in:
Tim 2025-02-11 16:29:31 -05:00 committed by GitHub
parent 83316b29ef
commit ced825c40f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
notebooks/1-Quickstart.ipynb
View File

@ -138,7 +138,7 @@
"source": [
"def upload_files(\n",
" file_directory: str,\n",
" storage_name: str,\n",
" container_name: str,\n",
" batch_size: int = 100,\n",
" overwrite: bool = True,\n",
" max_retries: int = 5,\n",
@ -147,10 +147,10 @@
" Upload files to a blob storage container.\n",
"\n",
" Args:\n",
" file_directory - a local directory of .txt files to upload. All files must have utf-8 encoding.\n",
" storage_name - a unique name for the Azure storage blob container.\n",
" file_directory - a local directory of .txt files to upload. All files must be in utf-8 encoding.\n",
" container_name - a unique name for the Azure storage container.\n",
" batch_size - the number of files to upload in a single batch.\n",
" overwrite - whether or not to overwrite files if they already exist in the storage blob container.\n",
" overwrite - whether or not to overwrite files if they already exist in the storage container.\n",
" max_retries - the maximum number of times to retry uploading a batch of files if the API is busy.\n",
"\n",
" NOTE: Uploading files may sometimes fail if the blob container was recently deleted\n",
@ -159,13 +159,13 @@
" url = endpoint + \"/data\"\n",
"\n",
" def upload_batch(\n",
" files: list, storage_name: str, overwrite: bool, max_retries: int\n",
" files: list, container_name: str, overwrite: bool, max_retries: int\n",
" ) -> requests.Response:\n",
" for _ in range(max_retries):\n",
" response = requests.post(\n",
" url=url,\n",
" files=files,\n",
" params={\"storage_name\": storage_name, \"overwrite\": overwrite},\n",
" params={\"container_name\": container_name, \"overwrite\": overwrite},\n",
" headers=headers,\n",
" )\n",
" # API may be busy, retry\n",
@ -194,20 +194,20 @@
" )\n",
" # upload batch of files\n",
" if len(batch_files) == batch_size:\n",
" response = upload_batch(batch_files, storage_name, overwrite, max_retries)\n",
" response = upload_batch(batch_files, container_name, overwrite, max_retries)\n",
" # if response is not ok, return early\n",
" if not response.ok:\n",
" return response\n",
" batch_files.clear()\n",
" # upload remaining files\n",
" if len(batch_files) > 0:\n",
" response = upload_batch(batch_files, storage_name, overwrite, max_retries)\n",
" response = upload_batch(batch_files, container_name, overwrite, max_retries)\n",
" return response\n",
"\n",
"\n",
"response = upload_files(\n",
" file_directory=file_directory,\n",
" storage_name=storage_name,\n",
" container_name=storage_name,\n",
" batch_size=100,\n",
" overwrite=True,\n",
")\n",
@ -240,8 +240,14 @@
" This function kicks off a job that builds a knowledge graph index from files located in a blob storage container.\n",
" \"\"\"\n",
" url = endpoint + \"/index\"\n",
" request = {\"storage_name\": storage_name, \"index_name\": index_name}\n",
" return requests.post(url, params=request, headers=headers)\n",
" return requests.post(\n",
" url,\n",
" params={\n",
" \"index_container_name\": index_name,\n",
" \"storage_container_name\": storage_name,\n",
" },\n",
" headers=headers,\n",
" )\n",
"\n",
"\n",
"response = build_index(storage_name=storage_name, index_name=index_name)\n",