Merge branch 'main' into jal/top-level-async

Author: jakelorocco

README.md

@@ -89,7 +89,7 @@ print(m.chat("What is the etymology of mellea?").content)
 
 Then run it:
 > [!NOTE]
-> Before we get started, you will need to download and install [ollama](https://ollama.com/). Mellea can work with many different types of backends, but everything in this tutorial will "just work" on a Macbook running IBM's Granite 3.3 8B model.
+> Before we get started, you will need to download and install [ollama](https://ollama.com/). Mellea can work with many different types of backends, but everything in this tutorial will "just work" on a Macbook running IBM's Granite 4 Micro 3B model.
 ```shell
 uv run --with mellea docs/examples/tutorial/example.py
 ```
@@ -128,13 +128,13 @@ uv venv .venv && source .venv/bin/activate
 Use `uv pip` to install from source with the editable flag:
 
 ```bash
-uv pip install -e .[all]
+uv pip install -e '.[all]'
 ```
 
 If you are planning to contribute to the repo, it would be good to have all the development requirements installed:
 
 ```bash
-uv pip install .[all] --group dev --group notebook --group docs
+uv pip install '.[all]' --group dev --group notebook --group docs
 ```
 
 or 
@@ -143,7 +143,7 @@ or
 uv sync --all-extras --all-groups
 ```
 
-Ensure that you install the precommit hooks:
+If you want to contribute, ensure that you install the precommit hooks:
 
 ```bash
 pre-commit install

docs/examples/instruct_validate_repair/101_email_comparison.py

@@ -2,7 +2,7 @@
 from mellea import start_session
 from mellea.backends.types import ModelOption
 
-# create a session using Granite 3.3 8B on Ollama and a simple context [see below]
+# create a session using Granite 4 Micro 3B on Ollama and a simple context [see below]
 m = start_session(model_options={ModelOption.MAX_NEW_TOKENS: 200})
 
 # Write a more formal and a more funny email

docs/examples/instruct_validate_repair/101_email_with_requirements.py

@@ -2,7 +2,7 @@
 from mellea import start_session
 from mellea.backends.types import ModelOption
 
-# create a session using Granite 3.3 8B on Ollama and a simple context [see below]
+# create a session using Granite 4 Micro 3B on Ollama and a simple context [see below]
 m = start_session(model_options={ModelOption.MAX_NEW_TOKENS: 200})
 
 # write an email with automatic requirement checking.

docs/examples/instruct_validate_repair/advanced_email_with_validate_function.py

@@ -4,7 +4,7 @@
 from mellea.stdlib.requirement import Requirement, simple_validate
 from mellea.stdlib.sampling import RejectionSamplingStrategy
 
-# create a session using Granite 3.3 8B on Ollama and a simple context [see below]
+# create a session using Granite 4 Micro 3B on Ollama and a simple context [see below]
 m = start_session(model_options={ModelOption.MAX_NEW_TOKENS: 200})
 
 # Define a requirement which checks that the output is less than 100 words

docs/examples/tutorial/simple_email.py

@@ -1,6 +1,6 @@
 import mellea
 
-# INFO: this line will download IBM's Granite 3.3 8B model.
+# INFO: this line will download IBM's Granite 4 Micro 3B model.
 m = mellea.start_session()
 
 print("Basic email:")

docs/tutorial.md

@@ -51,7 +51,7 @@ Although good generative programs can be written in any language and framework,
 
 ## Chapter 2: Getting Started with Generative Programming in Mellea
 
-Before we get started, you will need to download and install [ollama](https://ollama.com/). Mellea can work with many different types of backends, but everything in this tutorial will "just work" on a Macbook running IBM's Granite 3.3 8B model.
+Before we get started, you will need to download and install [ollama](https://ollama.com/). Mellea can work with many different types of backends, but everything in this tutorial will "just work" on a Macbook running IBM's Granite 4 Micro 3B model.
 
 We also recommend that you download and install [uv](https://docs.astral.sh/uv/#installation). You can run any of the examples in the tutorial with:
 ```bash
@@ -69,7 +69,7 @@ Once you have ollama installed and running, we can get started with our first ge
 # file: https://github.com/generative-computing/mellea/blob/main/docs/examples/tutorial/simple_email.py#L1-L8
 import mellea
 
-# INFO: this line will download IBM's Granite 3.3 8B model.
+# INFO: this line will download IBM's Granite 4 Micro 3B model.
 m = mellea.start_session()
 
 email = m.instruct("Write an email inviting interns to an office party at 3:30pm.")