version 0.0.3

Author: Johannes Hötter

README.md

@@ -1,14 +1,14 @@
 ![kern-python](https://uploads-ssl.webflow.com/61e47fafb12bd56b40022a49/62766400bd3c57b579d289bf_kern-python%20Banner.png)
 [![Python 3.9](https://img.shields.io/badge/python-3.9-blue.svg)](https://www.python.org/downloads/release/python-390/)
-[![pypi 0.0.1](https://img.shields.io/badge/pypi-0.0.1-yellow.svg)](https://pypi.org/project/kern-python-client/0.0.1/)
+[![pypi 0.0.3](https://img.shields.io/badge/pypi-0.0.3-yellow.svg)](https://pypi.org/project/kern-sdk/0.0.3/)
 
 # Kern AI API for Python
 
 This is the official Python SDK for Kern AI, your IDE for programmatic data enrichment and management.
 
 ## Installation
 
-You can set up this library via either running `$ pip install kern-sdk`, or via cloning this repository and running `$ pip install -r requirements.txt` in your repository.
+You can set up this library via either running `$ pip install kern-sdk`, or via cloning this repository and running `$ pip install -r requirements.txt` in this repository.
 
 ## Usage
 Once you installed the package, you can access the application from any Python terminal as follows:
@@ -25,11 +25,23 @@ client = Client(username, password, project_id)
 # client = Client(username, password, project_id, uri="http://localhost:4455")
 ```
 
+Alternatively, you can provide a `secrets.json` file in your repository, looking as follows:
+```json
+{
+    "user_name": "your-username",
+    "password": "your-password",
+    "project_id": "your-project-id"
+}
+```
+Again, if you run on your local machine, you should provide also `"uri": "http://localhost:4455"`.
+
 Now, you can easily fetch the data from your project:
 ```python
-df = client.fetch_export()
+df = client.get_record_export()
 ```
 
+Alternatively, you can also just run `kern pull` in your CLI given that you have provided the `secrets.json` file.
+
 The `df` contains data of the following scheme:
 - all your record attributes are stored as columns, e.g. `headline` or `running_id` if you uploaded records like `{"headline": "some text", "running_id": 1234}`
 - per labeling task three columns:
@@ -41,7 +53,8 @@ With the `client`, you easily integrate your data into any kind of system; may i
 
 ## Roadmap
 - [ ] Register information sources via wrappers
-- [ ] Fetch project statistics
+- [ ] Add project upload
+- [x] Fetch project statistics
 
 
 If you want to have something added, feel free to open an [issue](https://github.com/code-kern-ai/kern-python/issues).

kern/__init__.py

@@ -3,7 +3,7 @@
 from wasabi import msg
 import pandas as pd
 from kern import authentication, api_calls, settings, exceptions
-from typing import Optional
+from typing import Optional, Dict
 import json
 
 
@@ -35,7 +35,7 @@ def __init__(
         self.project_id = project_id
 
     @classmethod
-    def from_secrets_file(cls, path_to_file):
+    def from_secrets_file(cls, path_to_file: str):
         with open(path_to_file, "r") as file:
             content = json.load(file)
         uri = content.get("uri")
@@ -48,7 +48,12 @@ def from_secrets_file(cls, path_to_file):
             uri=uri,
         )
 
-    def get_project_details(self):
+    def get_project_details(self) -> Dict[str, str]:
+        """Collect high-level information about your project: name, description, and tokenizer
+
+        Returns:
+            Dict[str, str]: dictionary containing the above information
+        """
         url = settings.get_project_url(self.project_id)
         api_response = api_calls.get_request(url, self.session_token)
         return api_response
@@ -62,7 +67,7 @@ def get_record_export(
             num_samples (Optional[int], optional): If set, only the first `num_samples` records are collected. Defaults to None.
 
         Returns:
-            pd.DataFrame: DataFrame containing your record data. For more details, see https://docs.kern.ai
+            pd.DataFrame: DataFrame containing your record data.
         """
         url = settings.get_export_url(self.project_id)
         api_response = api_calls.get_request(
@@ -74,29 +79,30 @@ def get_record_export(
             msg.good(f"Downloaded export to {download_to}")
         return df
 
-    def post_file_import(self, upload_from: str):
-        upload_from = f"{upload_from}_SCALE"
-        file_type = "records"
-        import_file_options = None
-        config_url = settings.get_config_url()
-        config_api_response = api_calls.get_request(config_url, self.session_token)
-        endpoint = config_api_response["KERN_S3_ENDPOINT"]
-
-        import_url = settings.get_import_url(self.project_id)
-        import_api_response = api_calls.post_request(
-            import_url,
-            {
-                "file_name": upload_from,
-                "file_type": file_type,
-                "import_file_options": import_file_options,
-            },
-            self.session_token,
-        )
+    # TODO: issue #6
+    # def post_file_import(self, upload_from: str):
+    #     upload_from = f"{upload_from}_SCALE"
+    #     file_type = "records"
+    #     import_file_options = None
+    #     config_url = settings.get_config_url()
+    #     config_api_response = api_calls.get_request(config_url, self.session_token)
+    #     endpoint = config_api_response["KERN_S3_ENDPOINT"]
+
+    #     import_url = settings.get_import_url(self.project_id)
+    #     import_api_response = api_calls.post_request(
+    #         import_url,
+    #         {
+    #             "file_name": upload_from,
+    #             "file_type": file_type,
+    #             "import_file_options": import_file_options,
+    #         },
+    #         self.session_token,
+    #     )
 
-        credentials = import_api_response["Credentials"]
-        access_key = credentials["AccessKeyId"]
-        secret_key = credentials["SecretAccessKey"]
-        session_token = credentials["SessionToken"]
+    #     credentials = import_api_response["Credentials"]
+    #     access_key = credentials["AccessKeyId"]
+    #     secret_key = credentials["SecretAccessKey"]
+    #     session_token = credentials["SessionToken"]
 
-        upload_task_id = import_api_response["uploadTaskId"]
-        return endpoint, access_key, secret_key, session_token, upload_task_id
+    #     upload_task_id = import_api_response["uploadTaskId"]
+    #     return endpoint, access_key, secret_key, session_token, upload_task_id

setup.py

@@ -10,7 +10,7 @@
 
 setup(
     name="kern-sdk",
-    version="0.0.2",
+    version="0.0.3",
     author="jhoetter",
     author_email="johannes.hoetter@kern.ai",
     description="Official SDK for the Kern AI API",