gmicloud 0.1.6__py3-none-any.whl → 0.1.9__py3-none-any.whl

gmicloud-0.1.9.dist-info/METADATA

@@ -0,0 +1,264 @@
+Metadata-Version: 2.4
+Name: gmicloud
+Version: 0.1.9
+Summary: GMI Cloud Python SDK
+Author-email: GMI <gmi@gmitec.net>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+
+# GMICloud SDK
+
+## Overview
+Before you start: Our service and GPU resource is currenly invite-only so please contact our team (getstarted@gmicloud.ai) to get invited if you don't have one yet.
+
+The GMI Inference Engine SDK provides a Python interface for deploying and managing machine learning models in production environments. It allows users to create model artifacts, schedule tasks for serving models, and call inference APIs easily.
+
+This SDK streamlines the process of utilizing GMI Cloud capabilities such as deploying models with Kubernetes-based Ray services, managing resources automatically, and accessing model inference endpoints. With minimal setup, developers can focus on building ML solutions instead of infrastructure.
+
+## Features
+
+- Artifact Management: Easily create, update, and manage ML model artifacts.
+- Task Management: Quickly create, schedule, and manage deployment tasks for model inference.
+- Usage Data Retrieval : Fetch and analyze usage data to optimize resource allocation.
+
+## Installation
+
+To install the SDK, use pip:
+
+```bash
+pip install gmicloud
+```
+
+## Setup
+
+You must configure authentication credentials for accessing the GMI Cloud API. 
+To create account and get log in info please visit **GMI inference platform: https://inference-engine.gmicloud.ai/**.
+
+There are two ways to configure the SDK:
+
+### Option 1: Using Environment Variables
+
+Set the following environment variables:
+
+```shell
+export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID> # Pick what every ID you need.
+export GMI_CLOUD_EMAIL=<YOUR_EMAIL>
+export GMI_CLOUD_PASSWORD=<YOUR_PASSWORD>
+```
+
+### Option 2: Passing Credentials as Parameters
+
+Pass `client_id`, `email`, and `password` directly to the Client object when initializing it in your script:
+
+```python
+from gmicloud import Client
+
+client = Client(client_id="<YOUR_CLIENT_ID>", email="<YOUR_EMAIL>", password="<YOUR_PASSWORD>")
+```
+
+## Quick Start
+
+### 1. How to run the code in the example folder
+```bash
+cd path/to/gmicloud-sdk
+# Create a virtual environment
+python -m venv venv
+source venv/bin/activate
+
+pip install -r requirements.txt
+python -m examples.create_task_from_artifact_template.py
+```
+
+### 2. Example of create an inference task from an artifact template
+
+This is the simplest example to deploy an inference task using an existing artifact template:
+
+Up-to-date code in /examples/create_task_from_artifact_template.py
+
+```python
+from datetime import datetime
+import os
+import sys
+
+from gmicloud import *
+from examples.completion import call_chat_completion
+
+cli = Client()
+
+# List templates offered by GMI cloud 
+templates = cli.list_templates()
+print(f"Found {len(templates)} templates: {templates}")
+
+# Pick a template from the list
+pick_template = "Llama-3.1-8B"
+
+# Create Artifact from template
+artifact_id, recommended_replica_resources = cli.create_artifact_from_template(templates[0])
+print(f"Created artifact {artifact_id} with recommended replica resources: {recommended_replica_resources}")
+
+# Create Task based on Artifact
+task_id = cli.create_task(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=1,
+    )
+))
+task = cli.task_manager.get_task(task_id)
+print(f"Task created: {task.config.task_name}. You can check details at https://inference-engine.gmicloud.ai/user-console/task")
+
+# Start Task and wait for it to be ready
+cli.start_task_and_wait(task.task_id)
+
+# Testing with calling chat completion
+print(call_chat_completion(cli, task.task_id))
+
+```
+
+### 3. Example of creating an inference task based on custom model with local vllm / SGLang serve command
+* Full example is available at [examples/inference_task_with_custom_model.py](https://github.com/GMISWE/python-sdk/blob/main/examples/inference_task_with_custom_model.py)
+
+1. Prepare custom model checkpoint (using a model downloaded from HF as an example)
+
+```python
+# Download model from huggingface
+from huggingface_hub import snapshot_download
+
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+model_checkpoint_save_dir = "files/model_garden"
+snapshot_download(repo_id=model_name, local_dir=model_checkpoint_save_dir)
+```
+
+#### Pre-downloaded models
+```
+"deepseek-ai/DeepSeek-R1"
+"deepseek-ai/DeepSeek-V3-0324"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+"meta-llama/Llama-3.3-70B-Instruct"
+"meta-llama/Llama-4-Maverick-17B-128E-Instruct"
+"meta-llama/Llama-4-Scout-17B-16E-Instruct"
+"Qwen/QwQ-32B"
+```
+
+2. Find a template of specific vllm or SGLang version
+
+```python
+# export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
+# export GMI_CLOUD_EMAIL=<YOUR_EMAIL>
+# export GMI_CLOUD_PASSWORD=<YOUR_PASSWORD>
+cli = Client()
+
+# List templates offered by GMI cloud 
+templates = cli.artifact_manager.list_public_template_names()
+print(f"Found {len(templates)} templates: {templates}")
+```
+
+3. Pick a template (e.g. SGLang 0.4.5) and prepare a local serve command
+
+```python
+# Example for vllm server
+picked_template_name = "gmi_vllm_0.8.4"
+serve_command = "vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --trust-remote-code --gpu-memory-utilization 0.8"
+
+# Example for sglang server
+picked_template_name = "gmi_sglang_0.4.5.post1"
+serve_command = "python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --trust-remote-code --mem-fraction-static 0.8 --tp 2"
+```
+
+4. Create an artifact. you can pass `pre_download_model` parameter. If you want custom model, upload model checkpoint to the artifactThe artifact can be reused to create inference tasks later. Artifact also suggests recommended resources for each inference server replica
+
+```python
+artifact_name = "artifact_hello_world"
+artifact_id, recommended_replica_resources = cli.artifact_manager.create_artifact_for_serve_command_and_custom_model(
+    template_name=picked_template_name,
+    artifact_name=artifact_name,
+    serve_command=serve_command,
+    gpu_type="H100",
+    artifact_description="This is a test artifact",
+    pre_download_model=pick_pre_downloaded_model,
+)
+print(f"Created artifact {artifact_id} with recommended resources: {recommended_replica_resources}")
+```
+
+Alternatively, Upload a custom model checkpoint to artifact
+```python
+cli.artifact_manager.upload_model_files_to_artifact(artifact_id, model_checkpoint_save_dir)
+
+# Maybe Wait 10 minutes for the artifact to be ready
+time.sleep(10 * 60)
+```
+
+5. Create Inference task (defining min/max inference replica), start and wait
+
+```python
+# Create Task based on Artifact
+new_task_id = cli.task_manager.create_task_from_artifact_id(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=4,
+    )
+))
+task = cli.task_manager.get_task(new_task_id)
+print(f"Task created: {task.config.task_name}. You can check details at https://inference-engine.gmicloud.ai/user-console/task")
+
+# Start Task and wait for it to be ready
+cli.task_manager.start_task_and_wait(new_task_id)
+```
+
+6. Test with sample chat completion request with OpenAI client
+
+```python
+pi_key = "<YOUR_API_KEY>"
+endpoint_url = cli.task_manager.get_task_endpoint_url(new_task_id)
+open_ai = OpenAI(
+    base_url=os.getenv("OPENAI_API_BASE", f"https://{endpoint_url}/serve/v1/"),
+    api_key=api_key
+)
+# Make a chat completion request using the new OpenAI client.
+completion = open_ai.chat.completions.create(
+    model=picked_template_name,
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Who are you?"},
+    ],
+    max_tokens=500,
+    temperature=0.7
+)
+print(completion.choices[0].message.content)
+```
+
+
+## API Reference
+
+### Client
+
+Represents the entry point to interact with GMI Cloud APIs.
+Client(
+client_id: Optional[str] = "",
+email: Optional[str] = "",
+password: Optional[str] = ""
+)
+
+### Artifact Management
+
+* get_artifact_templates(): Fetch a list of available artifact templates.
+* create_artifact_from_template(template_id: str): Create a model artifact from a given template.
+* get_artifact(artifact_id: str): Get details of a specific artifact.
+
+### Task Management
+
+* create_task_from_artifact_template(template_id: str, scheduling: TaskScheduling): Create and schedule a task using an
+  artifact template.
+* start_task(task_id: str): Start a task.
+* get_task(task_id: str): Retrieve the status and details of a specific task.
+
+## Notes & Troubleshooting

gmicloud-0.1.9.dist-info/RECORD

@@ -0,0 +1,31 @@
+gmicloud/__init__.py,sha256=xSzrAxiby5Te20yhy1ZylGHmQKVV_w1QjFe6D99VZxw,968
+gmicloud/client.py,sha256=nTMrKhyrGSx9qUDTice2HqmIqlIlsuKoxHnb0T-Ls3c,10947
+gmicloud/_internal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gmicloud/_internal/_config.py,sha256=BenHiCnedpHA5phz49UWBXa1mg_q9W8zYs7A8esqGcU,494
+gmicloud/_internal/_constants.py,sha256=Y085dwFlqdFkCf39iBfxz39QiiB7lX59ayNJjB86_m4,378
+gmicloud/_internal/_enums.py,sha256=aN3At0_iV_6aaUsrOy-JThtRUokeY4nTyxxPLZmIDBU,1093
+gmicloud/_internal/_exceptions.py,sha256=hScBq7n2fOit4_umlkabZJchY8zVbWSRfWM2Y0rLCbw,306
+gmicloud/_internal/_models.py,sha256=iSRHMUPx_iXEraSg3ouAIM4ipVXQop3MuCGJFvFvMLY,25011
+gmicloud/_internal/_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gmicloud/_internal/_client/_artifact_client.py,sha256=0lyHAdUybN8A1mEwZ7p1yK2yQEyoDG2vTB4Qe5RI2ik,9974
+gmicloud/_internal/_client/_auth_config.py,sha256=zlCUPHN_FgWmOAxOAgjBtGRbaChqMa9PPGPuVNKvnc8,2700
+gmicloud/_internal/_client/_decorator.py,sha256=sy4gxzsUB6ORXHw5pqmMf7TTlK41Nmu1fhIhK2AIsbY,670
+gmicloud/_internal/_client/_file_upload_client.py,sha256=r29iXG_0DOi-uTLu9plpfZMWGqOck_AdDHJZprcf8uI,4918
+gmicloud/_internal/_client/_http_client.py,sha256=j--3emTjJ_l9CTdnkTbcpf7gYcUEl341pv2O5cU67l0,5741
+gmicloud/_internal/_client/_iam_client.py,sha256=iXam-UlTCJWCpXmxAhqCo0J2m6nPzNOWa06R5xAy5nQ,8297
+gmicloud/_internal/_client/_task_client.py,sha256=69OqZC_kwSDkTSVVyi51Tn_OyUV6R0nin4z4gLfZ-Lg,6141
+gmicloud/_internal/_client/_video_client.py,sha256=bjSmChBydGXwuVIm37ltKGmduPJa-H0Bjyc-qhd_PZI,4694
+gmicloud/_internal/_manager/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gmicloud/_internal/_manager/_artifact_manager.py,sha256=Fq5Qifrdq5yn_QkMAoykuWE04FgqNOd9yZrFQdAi5J8,21874
+gmicloud/_internal/_manager/_iam_manager.py,sha256=nAqPCaUfSXTnx2MEQa8e0YUOBFYWDRiETgK1PImdf4o,1167
+gmicloud/_internal/_manager/_task_manager.py,sha256=g2K0IG1EXzcZRAfXLhUp78em0ZVvKyqlr1PGTBR04JQ,12501
+gmicloud/_internal/_manager/_video_manager.py,sha256=_PwooKf9sZkIx4mYTy57pXtP7J3uwHQHgscns5hQYZ0,3376
+gmicloud/_internal/_manager/serve_command_utils.py,sha256=0PXDRuGbLw_43KBwCxPRdb4QqijZrzYyvM6WOZ2-Ktg,4583
+gmicloud/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gmicloud/tests/test_artifacts.py,sha256=w0T0EpATIGLrSUPaBfTZ2ZC_X2XeaTlFEi3DZ4evIcE,15825
+gmicloud/tests/test_tasks.py,sha256=yL-aFf80ShgTyxEONTWh-xbWDf5XnUNtIeA5hYvhKM0,10963
+gmicloud/utils/uninstall_packages.py,sha256=zzuuaJPf39oTXWZ_7tUAGseoxocuCbbkoglJSD5yDrE,1127
+gmicloud-0.1.9.dist-info/METADATA,sha256=sZlrvpl2xiwBoVJj79IQ0JIFXg8md9mCmA13P99dXj0,9028
+gmicloud-0.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+gmicloud-0.1.9.dist-info/top_level.txt,sha256=AZimLw3y0WPpLiSiOidZ1gD0dxALh-jQNk4fxC05hYE,9
+gmicloud-0.1.9.dist-info/RECORD,,

{gmicloud-0.1.6.dist-info → gmicloud-0.1.9.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

gmicloud-0.1.6.dist-info/METADATA

@@ -1,147 +0,0 @@
-Metadata-Version: 2.2
-Name: gmicloud
-Version: 0.1.6
-Summary: GMI Cloud Python SDK
-Author-email: GMI <support@gmicloud.ai>
-License: MIT
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-
-# GMICloud SDK (Beta)
-
-## Overview
-Before you start: Our service and GPU resource is currenly invite-only so please contact our team (getstarted@gmicloud.ai) to get invited if you don't have one yet.
-
-The GMI Inference Engine SDK provides a Python interface for deploying and managing machine learning models in production environments. It allows users to create model artifacts, schedule tasks for serving models, and call inference APIs easily.
-
-This SDK streamlines the process of utilizing GMI Cloud capabilities such as deploying models with Kubernetes-based Ray services, managing resources automatically, and accessing model inference endpoints. With minimal setup, developers can focus on building ML solutions instead of infrastructure.
-
-## Features
-
-- Artifact Management: Easily create, update, and manage ML model artifacts.
-- Task Management: Quickly create, schedule, and manage deployment tasks for model inference.
-- Usage Data Retrieval : Fetch and analyze usage data to optimize resource allocation.
-
-## Installation
-
-To install the SDK, use pip:
-
-```bash
-pip install gmicloud
-```
-
-## Setup
-
-You must configure authentication credentials for accessing the GMI Cloud API. 
-To create account and get log in info please visit **GMI inference platform: https://inference-engine.gmicloud.ai/**.
-
-There are two ways to configure the SDK:
-
-### Option 1: Using Environment Variables
-
-Set the following environment variables:
-
-```shell
-export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
-export GMI_CLOUD_EMAIL=<YOUR_EMAIL>
-export GMI_CLOUD_PASSWORD=<YOUR_PASSWORD>
-```
-
-### Option 2: Passing Credentials as Parameters
-
-Pass `client_id`, `email`, and `password` directly to the Client object when initializing it in your script:
-
-```python
-from gmicloud import Client
-
-client = Client(client_id="<YOUR_CLIENT_ID>", email="<YOUR_EMAIL>", password="<YOUR_PASSWORD>")
-```
-
-## Quick Start
-
-### 1. How to run the code in the example folder
-```bash
-cd path/to/gmicloud-sdk
-# Create a virtual environment
-python -m venv venv
-source venv/bin/activate
-
-pip install -r requirements.txt
-python -m examples.create_task_from_artifact_template.py
-```
-
-### 2. Create an inference task from an artifact template
-
-This is the simplest example to deploy an inference task using an existing artifact template:
-
-Up-to-date code in /examples/create_task_from_artifact_template.py
-
-```python
-from datetime import datetime
-import os
-import sys
-
-from gmicloud import *
-from examples.completion import call_chat_completion
-
-cli = Client()
-
-# List templates offered by GMI cloud 
-templates = cli.list_templates()
-print(f"Found {len(templates)} templates: {templates}")
-
-# Pick a template from the list
-pick_template = "Llama-3.1-8B"
-
-# Create Artifact from template
-artifact_id, recommended_replica_resources = cli.create_artifact_from_template(templates[0])
-print(f"Created artifact {artifact_id} with recommended replica resources: {recommended_replica_resources}")
-
-# Create Task based on Artifact
-task_id = cli.create_task(artifact_id, recommended_replica_resources, TaskScheduling(
-    scheduling_oneoff=OneOffScheduling(
-        trigger_timestamp=int(datetime.now().timestamp()),
-        min_replicas=1,
-        max_replicas=1,
-    )
-))
-task = cli.task_manager.get_task(task_id)
-print(f"Task created: {task.config.task_name}. You can check details at https://inference-engine.gmicloud.ai/user-console/task")
-
-# Start Task and wait for it to be ready
-cli.start_task_and_wait(task.task_id)
-
-# Testing with calling chat completion
-print(call_chat_completion(cli, task.task_id))
-
-```
-
-## API Reference
-
-### Client
-
-Represents the entry point to interact with GMI Cloud APIs.
-Client(
-client_id: Optional[str] = "",
-email: Optional[str] = "",
-password: Optional[str] = ""
-)
-
-### Artifact Management
-
-* get_artifact_templates(): Fetch a list of available artifact templates.
-* create_artifact_from_template(template_id: str): Create a model artifact from a given template.
-* get_artifact(artifact_id: str): Get details of a specific artifact.
-
-### Task Management
-
-* create_task_from_artifact_template(template_id: str, scheduling: TaskScheduling): Create and schedule a task using an
-  artifact template.
-* start_task(task_id: str): Start a task.
-* get_task(task_id: str): Retrieve the status and details of a specific task.
-
-## Notes & Troubleshooting
-k

gmicloud-0.1.6.dist-info/RECORD

@@ -1,27 +0,0 @@
-gmicloud/__init__.py,sha256=aIgu4MAw4nExv781-pzSZLG8MscqAMZ5lM5fGyqg7QU,984
-gmicloud/client.py,sha256=G0tD0xQnpqDKS-3l-AAU-K3FAHOsqsTzsAq2NVxiamY,10539
-gmicloud/_internal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gmicloud/_internal/_config.py,sha256=qIH76TSyS3MQWe62LHI46RJhDnklNFisdajY75oUAqE,218
-gmicloud/_internal/_constants.py,sha256=Y085dwFlqdFkCf39iBfxz39QiiB7lX59ayNJjB86_m4,378
-gmicloud/_internal/_enums.py,sha256=5d6Z8TFJYCmhNI1TDbPpBbG1tNe96StIEH4tEw20RZk,789
-gmicloud/_internal/_exceptions.py,sha256=hScBq7n2fOit4_umlkabZJchY8zVbWSRfWM2Y0rLCbw,306
-gmicloud/_internal/_models.py,sha256=eArBzdhiMosLVZVUyoE_mvfxRS8yKPkuqhlDaa57Iog,17863
-gmicloud/_internal/_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gmicloud/_internal/_client/_artifact_client.py,sha256=-CyMdTauVovuv3whs8yUqmv3-WW2e9m2GoEG9D6eNbc,8374
-gmicloud/_internal/_client/_decorator.py,sha256=sy4gxzsUB6ORXHw5pqmMf7TTlK41Nmu1fhIhK2AIsbY,670
-gmicloud/_internal/_client/_file_upload_client.py,sha256=1JRs4X57S3EScPIP9w2DC1Uo6_Wbcjumcw3nVM7uIGM,4667
-gmicloud/_internal/_client/_http_client.py,sha256=j--3emTjJ_l9CTdnkTbcpf7gYcUEl341pv2O5cU67l0,5741
-gmicloud/_internal/_client/_iam_client.py,sha256=pgOXIqp9aJvcIUCEVkYPEyMUyxBftecojHAbs8Gbl94,7013
-gmicloud/_internal/_client/_task_client.py,sha256=69OqZC_kwSDkTSVVyi51Tn_OyUV6R0nin4z4gLfZ-Lg,6141
-gmicloud/_internal/_manager/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gmicloud/_internal/_manager/_artifact_manager.py,sha256=TBvGps__Kk1Ym7jztY3tNZ3XomKPrDIFPV7XyyLwHuw,15941
-gmicloud/_internal/_manager/_iam_manager.py,sha256=nAqPCaUfSXTnx2MEQa8e0YUOBFYWDRiETgK1PImdf4o,1167
-gmicloud/_internal/_manager/_task_manager.py,sha256=YDUcAdRkJhGumA1LLfpXfYs6jmLnev8P27UItPZHUBs,11268
-gmicloud/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gmicloud/tests/test_artifacts.py,sha256=q1jiTk5DN4G3LCLCO_8KbWArdc6RG3sETe1MCEt-vbI,16979
-gmicloud/tests/test_tasks.py,sha256=yL-aFf80ShgTyxEONTWh-xbWDf5XnUNtIeA5hYvhKM0,10963
-gmicloud/utils/uninstall_packages.py,sha256=zzuuaJPf39oTXWZ_7tUAGseoxocuCbbkoglJSD5yDrE,1127
-gmicloud-0.1.6.dist-info/METADATA,sha256=rqwbl1_3RfzhdBpn9eb3u1My3pk10k7T3r23oEiTshY,4675
-gmicloud-0.1.6.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-gmicloud-0.1.6.dist-info/top_level.txt,sha256=AZimLw3y0WPpLiSiOidZ1gD0dxALh-jQNk4fxC05hYE,9
-gmicloud-0.1.6.dist-info/RECORD,,