kiln-ai 0.8.1__tar.gz → 0.12.0__tar.gz

{kiln_ai-0.8.1 → kiln_ai-0.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kiln-ai
-Version: 0.8.1
+Version: 0.12.0
 Summary: Kiln AI
 Project-URL: Homepage, https://getkiln.ai
 Project-URL: Repository, https://github.com/Kiln-AI/kiln
@@ -19,8 +19,7 @@ Requires-Dist: jsonschema>=4.23.0
 Requires-Dist: langchain-aws>=0.2.4
 Requires-Dist: langchain-fireworks>=0.2.5
 Requires-Dist: langchain-groq>=0.2.0
-Requires-Dist: langchain-ollama>=0.2.0
-Requires-Dist: langchain-openai>=0.2.4
+Requires-Dist: langchain-ollama>=0.2.2
 Requires-Dist: langchain>=0.3.5
 Requires-Dist: openai>=1.53.0
 Requires-Dist: pdoc>=15.0.0
@@ -72,7 +71,8 @@ The library has a [comprehensive set of docs](https://kiln-ai.github.io/Kiln/kil
   - [Load an Existing Dataset into a Kiln Task Dataset](#load-an-existing-dataset-into-a-kiln-task-dataset)
   - [Using your Kiln Dataset in a Notebook or Project](#using-your-kiln-dataset-in-a-notebook-or-project)
   - [Using Kiln Dataset in Pandas](#using-kiln-dataset-in-pandas)
-- [Advanced Usage](#advanced-usage)
+  - [Building and Running a Kiln Task from Code](#building-and-running-a-kiln-task-from-code)
+- [Full API Reference](#full-api-reference)
 
 ## Installation
 
@@ -95,11 +95,14 @@ The Kiln Python library provides a set of Python classes that which help you eas
 
 ### Datamodel Overview
 
+Here's a high level overview of the Kiln datamodel. A project folder will reflect this nested structure:
+
 - Project: a Kiln Project that organizes related tasks
   - Task: a specific task including prompt instructions, input/output schemas, and requirements
     - TaskRun: a sample (run) of a task including input, output and human rating information
-    - DatasetSplit: a frozen collection of task runs divided into train/test/validation splits
     - Finetune: configuration and status tracking for fine-tuning models on task data
+    - Prompt: a prompt for this task
+    - DatasetSplit: a frozen collection of task runs divided into train/test/validation splits
 
 ### Load a Project
 
@@ -230,8 +233,43 @@ final_df = pd.concat(dfs, ignore_index=True)
 print(final_df)
 ```
 
-### Advanced Usage
+### Building and Running a Kiln Task from Code
+
+```python
+# Step 1: Create or Load a Task -- choose one of the following 1.A or 1.B
+
+# Step 1.A: Optionally load an existing task from disk
+# task = datamodel.Task.load_from_file("path/to/task.kiln")
+
+# Step 1.B: Create a new task in code, without saving to disk.
+task = datamodel.Task(
+    name="test task",
+    instruction="Tell a joke, given a subject.",
+)
+# replace with a valid JSON schema https://json-schema.org for your task (json string, not a python dict).
+# Or delete this line to use plaintext output
+task.output_json_schema = json_joke_schema
+
+# Step 2: Create an Adapter to run the task, with a specific model and provider
+adapter = adapter_for_task(task, model_name="llama_3_1_8b", provider="groq")
+
+# Step 3: Invoke the Adapter to run the task
+task_input = "cows"
+response = await adapter.invoke(task_input)
+print(f"Output: {response.output.output}")
+
+# Step 4 (optional): Load the task from disk and print the results.
+#  This will only work if the task was loaded from disk, or you called task.save_to_file() before invoking the adapter (epemerial tasks don't save their result to disk)
+task = datamodel.Task.load_from_file(tmp_path / "test_task.kiln")
+for run in task.runs():
+    print(f"Run: {run.id}")
+    print(f"Input: {run.input}")
+    print(f"Output: {run.output}")
+
+```
+
+## Full API Reference
 
 The library can do a lot more than the examples we've shown here.
 
-See the [docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) for more information.
+See the full API reference in the [docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) under the `Submodules` section of the sidebar.

{kiln_ai-0.8.1 → kiln_ai-0.12.0}/README.md

@@ -39,7 +39,8 @@ The library has a [comprehensive set of docs](https://kiln-ai.github.io/Kiln/kil
   - [Load an Existing Dataset into a Kiln Task Dataset](#load-an-existing-dataset-into-a-kiln-task-dataset)
   - [Using your Kiln Dataset in a Notebook or Project](#using-your-kiln-dataset-in-a-notebook-or-project)
   - [Using Kiln Dataset in Pandas](#using-kiln-dataset-in-pandas)
-- [Advanced Usage](#advanced-usage)
+  - [Building and Running a Kiln Task from Code](#building-and-running-a-kiln-task-from-code)
+- [Full API Reference](#full-api-reference)
 
 ## Installation
 
@@ -62,11 +63,14 @@ The Kiln Python library provides a set of Python classes that which help you eas
 
 ### Datamodel Overview
 
+Here's a high level overview of the Kiln datamodel. A project folder will reflect this nested structure:
+
 - Project: a Kiln Project that organizes related tasks
   - Task: a specific task including prompt instructions, input/output schemas, and requirements
     - TaskRun: a sample (run) of a task including input, output and human rating information
-    - DatasetSplit: a frozen collection of task runs divided into train/test/validation splits
     - Finetune: configuration and status tracking for fine-tuning models on task data
+    - Prompt: a prompt for this task
+    - DatasetSplit: a frozen collection of task runs divided into train/test/validation splits
 
 ### Load a Project
 
@@ -197,8 +201,43 @@ final_df = pd.concat(dfs, ignore_index=True)
 print(final_df)
 ```
 
-### Advanced Usage
+### Building and Running a Kiln Task from Code
+
+```python
+# Step 1: Create or Load a Task -- choose one of the following 1.A or 1.B
+
+# Step 1.A: Optionally load an existing task from disk
+# task = datamodel.Task.load_from_file("path/to/task.kiln")
+
+# Step 1.B: Create a new task in code, without saving to disk.
+task = datamodel.Task(
+    name="test task",
+    instruction="Tell a joke, given a subject.",
+)
+# replace with a valid JSON schema https://json-schema.org for your task (json string, not a python dict).
+# Or delete this line to use plaintext output
+task.output_json_schema = json_joke_schema
+
+# Step 2: Create an Adapter to run the task, with a specific model and provider
+adapter = adapter_for_task(task, model_name="llama_3_1_8b", provider="groq")
+
+# Step 3: Invoke the Adapter to run the task
+task_input = "cows"
+response = await adapter.invoke(task_input)
+print(f"Output: {response.output.output}")
+
+# Step 4 (optional): Load the task from disk and print the results.
+#  This will only work if the task was loaded from disk, or you called task.save_to_file() before invoking the adapter (epemerial tasks don't save their result to disk)
+task = datamodel.Task.load_from_file(tmp_path / "test_task.kiln")
+for run in task.runs():
+    print(f"Run: {run.id}")
+    print(f"Input: {run.input}")
+    print(f"Output: {run.output}")
+
+```
+
+## Full API Reference
 
 The library can do a lot more than the examples we've shown here.
 
-See the [docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) for more information.
+See the full API reference in the [docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) under the `Submodules` section of the sidebar.