Release/v0.22.0 (#194)

* Install griptape from dev

* Install all extras

* Add extras

* Update again

* Fix argument name

* Parameterize snippts

* Ignore test, update id

* Don't fail fast

* Fix examples

* Fixes

* Fix env variables, imports

* Fix variable names

* Ignore running sagemaker examples

* Rename utils

* Remove mktestdocs

.github/actions/init-environment/action.yml

@@ -26,13 +26,9 @@ runs:
 
       - name: Install dependencies
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction --no-root --with docs --with test
+        run: poetry install --no-interaction --no-root --with docs --with test --all-extras
         shell: bash
 
-      - name: Install project
-        run: poetry install --no-interaction --with docs --with test
-        shell: bash
-
       - name: Activate venv 
         run: |
           source .venv/bin/activate

.github/workflows/integration-tests.yml

@@ -70,11 +70,13 @@ jobs:
       GOOGLE_OWNER_EMAIL: ${{ secrets.INTEG_GOOGLE_OWNER_EMAIL }}
       LEONARDO_API_KEY: ${{ secrets.INTEG_LEONARDO_API_KEY }}
       LEONARDO_MODEL_ID: ${{ secrets.INTEG_LEONARDO_MODEL_ID }}
+      SAGEMAKER_TENSORFLOW_HUB_MODEL: ${{ secrets.INTEG_SAGEMAKER_TENSORFLOW_HUB_MODEL }}
+      SAGEMAKER_HUGGINGFACE_MODEL: ${{ secrets.INTEG_SAGEMAKER_HUGGINGFACE_MODEL }}
 
     steps:
       - name: Checkout actions
         uses: actions/checkout@v3
       - name: Init environment 
         uses: ./.github/actions/init-environment 
       - name: Run integration tests
-        run: pytest -xvs tests/integration
+        run: pytest -vs tests/integration

docs/griptape-framework/data/embedding-drivers.md

@@ -76,7 +76,7 @@ driver = HuggingFaceHubEmbeddingDriver(
     ),
 )
 
-results = driver.embed_string("Hello world!")
+embeddings = driver.embed_string("Hello world!")
 
 # display the first 3 embeddings
 print(embeddings[:3])
@@ -94,32 +94,32 @@ The [AmazonSageMakerEmbeddingDriver](../../reference/griptape/drivers/embedding/
     This driver requires the `drivers-embedding-amazon-sagemaker` [extra](../index.md#extras).
 
 ##### TensorFlow Hub Models
-```python
+```python ignore
 import os
-from griptape.drivers import HuggingFaceHubEmbeddingDriver
+from griptape.drivers import AmazonSageMakerEmbeddingDriver, SageMakerTensorFlowHubEmbeddingModelDriver
 
-embedding_driver=AmazonSageMakerEmbeddingDriver(
+driver = AmazonSageMakerEmbeddingDriver(
     model=os.environ["SAGEMAKER_TENSORFLOW_HUB_MODEL"],
     embedding_model_driver=SageMakerTensorFlowHubEmbeddingModelDriver(),
 )
 
-results = driver.embed_string("Hello world!")
+embeddings = driver.embed_string("Hello world!")
 
 # display the first 3 embeddings
 print(embeddings[:3])
 ```
 
 ##### HuggingFace Models
-```python
+```python ignore
 import os
-from griptape.drivers import HuggingFaceHubEmbeddingDriver
+from griptape.drivers import AmazonSageMakerEmbeddingDriver, SageMakerHuggingFaceEmbeddingModelDriver
 
-embedding_driver=AmazonSageMakerEmbeddingDriver(
+driver = AmazonSageMakerEmbeddingDriver(
     model=os.environ["SAGEMAKER_HUGGINGFACE_MODEL"],
-    embedding_model_driver=SageMakerTensorFlowHubEmbeddingModelDriver(),
+    embedding_model_driver=SageMakerHuggingFaceEmbeddingModelDriver(),
 )
 
-results = driver.embed_string("Hello world!")
+embeddings = driver.embed_string("Hello world!")
 
 # display the first 3 embeddings
 print(embeddings[:3])

docs/griptape-framework/structures/prompt-drivers.md

@@ -70,7 +70,7 @@ agent = Agent(
     prompt_driver=OpenAiChatPromptDriver(
         api_key=os.environ["OPENAI_API_KEY"],
         temperature=0.1,
-        model="gpt-3.5-turbo-16k",
+        model="gpt-3.5-turbo",
         response_format="json_object",
         seed=42,
     ),
@@ -271,7 +271,7 @@ agent.run("Hello Girafatron, what is your favorite animal?")
 
 The [HuggingFaceHubPromptDriver](#hugging-face-hub) also supports [Text Generation Interface](https://huggingface.co/docs/text-generation-inference/basic_tutorials/consuming_tgi#inference-client) for running models locally. To use Text Generation Interface, just set `model` to a TGI endpoint.
 
-```python
+```python ignore
 import os
 from griptape.structures import Agent
 from griptape.drivers import HuggingFaceHubPromptDriver
@@ -370,7 +370,7 @@ from griptape.drivers import (
     AmazonSageMakerPromptDriver,
     SageMakerLlamaPromptModelDriver,
 )
-from griptape.structures.structure import Rule
+from griptape.rules import Rule
 
 agent = Agent(
     prompt_driver=AmazonSageMakerPromptDriver(

docs/griptape-framework/structures/rulesets.md

@@ -35,9 +35,9 @@ pipeline = Pipeline(
 )
 
 pipeline.add_tasks(
-    PromptTask(input_template="Respond to this user's question: {{ args[0] }}"),
+    PromptTask(input="Respond to this user's question: {{ args[0] }}"),
     PromptTask(
-        input_template="Extract keywords from this response: {{ parent_output }}"
+        input="Extract keywords from this response: {{ parent_output }}"
     ),
 )
 
@@ -114,7 +114,7 @@ pipeline = Pipeline()
 
 pipeline.add_tasks(
     PromptTask(
-        input_template="Respond to the following prompt: {{ args[0] }}",
+        input="Respond to the following prompt: {{ args[0] }}",
         rulesets=[
             Ruleset(
                 name="Emojis",
@@ -125,7 +125,7 @@ pipeline.add_tasks(
         ]
     ),
     PromptTask(
-        input_template="Determine the sentiment of the following text: {{ parent_output }}",
+        input="Determine the sentiment of the following text: {{ parent_output }}",
         rulesets=[
             Ruleset(
                 name="Diacritic",

docs/griptape-framework/structures/tasks.md

@@ -4,8 +4,8 @@ A [Task](../../reference/griptape/tasks/index.md) is a purpose-built abstraction
 
 
 ## Context
-Tasks that take input have a field [input_template](../../reference/griptape/tasks/base_text_input_task.md#griptape.tasks.base_text_input_task.BaseTextInputTask.input_template) which lets you define the Task objective. 
-Within the [input_template](../../reference/griptape/tasks/base_text_input_task.md#griptape.tasks.base_text_input_task.BaseTextInputTask.input_template), you can access the following [context](../../reference/griptape/structures/structure.md#griptape.structures.structure.Structure.context) variables:
+Tasks that take input have a field [input](../../reference/griptape/tasks/base_text_input_task.md#griptape.tasks.base_text_input_task.BaseTextInputTask.input) which lets you define the Task objective. 
+Within the [input](../../reference/griptape/tasks/base_text_input_task.md#griptape.tasks.base_text_input_task.BaseTextInputTask.input), you can access the following [context](../../reference/griptape/structures/structure.md#griptape.structures.structure.Structure.context) variables:
 
 * `args`: an array of arguments passed to the `.run()` method.
 * `structure`: the structure that the task belongs to.

docs/griptape-tools/custom-tools/index.md

@@ -30,7 +30,7 @@ To add Python dependencies for your tool, add a `requirements.txt` file. The too
 
 Next, create a `tool.py` file with the following code:
 
-```python
+```python ignore
 import random
 from griptape.artifacts import TextArtifact
 from griptape.tools import BaseTool
@@ -58,7 +58,7 @@ class RandomNumberGenerator(BaseTool):
 
 Finally, let's test our tool:
 
-```python
+```python ignore
 from griptape.structures import Agent
 from rng_tool.tool import RandomNumberGenerator
 

docs/griptape-tools/index.md

@@ -2,7 +2,7 @@ Tools give the LLM abilities to invoke outside APIs, reference data sets, and ge
 
 Griptape tools are special Python classes that LLMs can use to accomplish specific goals. Here is an example custom tool for generating a random number:
 
-```python
+```python ignore
 import random
 from griptape.artifacts import TextArtifact
 from griptape.tools import BaseTool
@@ -30,7 +30,7 @@ A tool can have many "activities" as denoted by the `@activity` decorator. Each
 
 Output artifacts from all tool activities (except for `InfoArtifact` and `ErrorArtifact`) go to short-term `TaskMemory`. To disable that behavior set the `off_prompt` tool parameter to `False`:
 
-```python
+```python ignore
 RandomNumberGenerator(off_prompt=False)
 ```