Prepare 2.0.0 release

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.0.3
+current_version = 2.0.0
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)
 serialize = 
 	{major}.{minor}.{patch}

CHANGELOG.md

@@ -4,23 +4,49 @@
 
 ## Unreleased
 
-#### Enhancements:
+## `2.0.0`
 
-- **Code refactoring**: Improved code organization and readability by extracting functions for crafting messages and generating smaller reprs with `craft_message`, `repr_genai_pandas`, and `repr_genai`. 🧰
-- **Enhanced pandas support**: Optimized DataFrame and Series representation for GPT-3 and GPT-4 by using Markdown format. 📊
-- **Token management**: Introduced a new module `tokens.py` with utility functions `num_tokens_from_messages` and `trim_messages_to_fit_token_limit` to handle token count and message trimming based on model limitations and your wallet. 💸
+### Enhancements:
 
-#### Changes:
+#### Added
 
-- `craft_user_message` now uses the new `craft_message` function.
-- `craft_output_message` now uses the new `repr_genai` function.
-- The `get_historical_context` function now accepts an additional `model` parameter to support different GPT models and has been updated to use `tokens.trim_messages_to_fit_token_limit`.
-- The `ignore_tokens` list now uses the term "first line" instead of "start" for clarity.
-- Introduced support for GPT-4 token counting and message trimming in `tokens.py`.
+- 🔄 Keep conversations flowing with `%%assist` (#66)
+- 🖼️ Emit suggestions as `Markdown` instead of creating new cells (#66)
+- 🚀 Model selection made easy with the `--model` flag for `%%assist` (#65)
+- 💡 Introducing `GenaiMarkdown` – a dynamic Markdown display (#61)
+- 📝 Create a `%%prompt` magic for setting the default prompts for assistance and exceptions (#71, #69)
 
-#### Bug Fixes:
+#### Changed
 
-- N/A
+- 🧪 Craft a more ipythonic context manager (#62, #66)
+  - Meet the new `Context` class: capture IPython history and make it ChatCompletion-friendly
+  - Farewell `get_historical_context`, hello `build_context`: context construction using the new Context class
+  - Reduce messages sent to GPT models by trimming based on estimated number of tokens (#57)
+
+- 🎯 Type annotations step in! (#59)
+
+
+#### Improved
+
+- 📏 Token length checks now available in %%assist (#57)
+- 🧹 Code refactoring: introducing `craft_message`, `repr_genai_pandas`, and `repr_genai` for more organized and readable code
+- 📈 Enhanced pandas support: optimized DataFrame and Series representation for Large Language Model consumption using Markdown format
+- 💰 Token management: a new module `tokens.py` featuring `num_tokens_from_messages` and `trim_messages_to_fit_token_limit` to help you stay within model limitations and budget
+- 📚 Update assist magic documentation (#70)
+
+#### Removed
+
+- 🚫 `%%assist` no longer generates new code cells. It now creates Markdown output instead (#66)
+  - Relatedly, `in-place` is no longer an option since we do not change the cells
+
+
+### Changes:
+
+- `craft_user_message` now relies on the new `craft_message` function
+- `craft_output_message` has been upgraded to use the new `repr_genai` function
+- `get_historical_context` now sports an additional `model` parameter and utilizes `tokens.trim_messages_to_fit_token_limit`
+- For clarity, the `ignore_tokens` list now uses the term "first line" instead of "start"
+- GPT-4 token counting and message trimming now supported in `tokens.py`
 
 ## `1.0.3`
 

genai/_version.py

@@ -1 +1 @@
-__version__ = "1.0.3"
+__version__ = "2.0.0"

pyproject.toml

@@ -5,7 +5,7 @@
 
 [tool.poetry]
 name = "genai"
-version = "1.0.3"
+version = "2.0.0"
 description = "Generative AI for IPython (enhance your code cells)"
 authors = ["Kyle Kelley <rgbkrk@gmail.com>"]
 maintainers = ["Kyle Kelley <rgbkrk@gmail.com>"]