Merge pull request #91 from Mirascope/release/v0.2.4

Release/v0.2.4

docs/README.md

@@ -98,39 +98,14 @@ print(prompt.messages)
 * **Convenience**: Tooling that is **clean**, **elegant**, and **delightful** that **you don't need to maintain**.
 * **Open**: Dedication to building **open-source tools** you can use with **your choice of LLM**.
 
-## Requirements
-
-**Pydantic** is the only strict requirement, which will be included automatically during installation.
-
-The Prompt CLI and LLM Convenience Wrappers have additional requirements, which you can opt-in to include if you're using those features.
-
 ## Installation
 
 Install Mirascope and start building with LLMs in minutes.
 
 ```sh
-$ pip install mirascope
-```
-
-This will install the `mirascope` package along with `pydantic`.
-
-To include extra dependencies, run:
-
-```sh
-$ pip install mirascope[cli] # Prompt CLI
-$ pip install mirascope[openai] # LLM Convenience Wrappers
-$ pip install mirascope[all] # All Extras
-```
-
-<details>
-<summary>For those using zsh, you'll need to escape brackets:</summary>
-
-```sh
-$ pip install mirascope\[all\]
+pip install mirascope
 ```
 
-</details>
-
 ## 🚨 Warning: Strong Opinion 🚨
 
 Prompt Engineering is engineering. Beyond basic illustrative examples, prompting quickly becomes complex. Separating prompts from the engineering workflow will only put limitations on what you can build with LLMs. We firmly believe that prompts are far more than "just f-strings" and thus require developer tools that are purpose-built for building these more complex prompts as easily as possible.
@@ -284,12 +259,18 @@ print(prompt)
 <p>Since the `Prompt`'s `str` method uses template, the above will work as expected.</p>
 </details>
 
+### Additional Examples
+
+If you're using our LLM convenience wrappers, you'll need to get an API key to use the model of your choice. [OpenAI Account Setup](https://platform.openai.com/docs/quickstart/account-setup) will walk you through how to get your OpenAI API Key. You can follow similar steps for the provider of your choice (e.g. [Anyscale](https://platform.openai.com/docs/quickstart/account-setup) or [Together](https://docs.together.ai/reference/authentication-1)), or you can use a raw client for non-OpenAI models, like [Mistral](https://docs.together.ai/reference/authentication-1).
+
 Because the `Prompt` class is built on top of `BaseModel`, prompts easily integrate with tools like [FastAPI](https://fastapi.tiangolo.com):
 
 <details>
 <summary>FastAPI Example</summary>
 
 ```python
+import os
+
 from fastapi import FastAPI
 from mirascope import OpenAIChat
 
@@ -313,6 +294,8 @@ You can also use the `Prompt` class with whichever LLM you want to use:
 <summary>Mistral Example</summary>
 
 ```python
+import os
+
 from mistralai.client import MistralClient
 from mistralai.models.chat_completion import ChatMessage
 
@@ -339,6 +322,8 @@ chat_response = client.chat(
 <summary>OpenAI Example</summary>
 
 ```python
+import os
+
 from openai import OpenAI
 
 from prompts import GreetingsPrompt

docs/concepts/llm_convenience_wrappers.md

@@ -15,7 +15,7 @@ Mirascope provides convenience wrappers around the OpenAI client to make writing
 
 ### Create
 
-You can initialize an [`OpenAIChat`](../api/chat/models.md#mirascope.chat.models.OpenAIChat) instance and call [`create`](../api/chat/models.md#mirascope.chat.models.OpenAIChat.create) to generate an [`OpenAIChatCompletion`](../api/chat/types.md#mirascope.chat.types.OpenAIChatCompletion):
+You can initialize an [`OpenAIChat`](../api/chat/models/openai_chat.md#mirascope.chat.models.openai_chat.OpenAIChat) instance and call [`create`](../api/chat/models/openai_chat.md#mirascope.chat.models.openai_chat.OpenAIChat.create) to generate an [`OpenAIChatCompletion`](../api/chat/types.md#mirascope.chat.types.OpenAIChatCompletion):
 
 ```python
 from mirascope import OpenAIChat, Prompt
@@ -104,7 +104,7 @@ recipe = recipe_by_chef_using("apples", "japanese")
 
 ### Streaming
 
-You can use the [`stream`](../api/chat/models.md#mirascope.chat.models.OpenAIChat.stream) method to stream a response. All this is doing is setting `stream=True` and providing the [`OpenAIChatCompletionChunk`](../api/chat/types.md#mirascope.chat.types.OpenAIChatCompletionChunk) convenience wrappers around the response chunks.
+You can use the [`stream`](../api/chat/models/openai_chat.md#mirascope.chat.models.openai_chat.OpenAIChat.stream) method to stream a response. All this is doing is setting `stream=True` and providing the [`OpenAIChatCompletionChunk`](../api/chat/types.md#mirascope.chat.types.OpenAIChatCompletionChunk) convenience wrappers around the response chunks.
 
 ```python
 chat = OpenAIChat()
@@ -132,7 +132,7 @@ chunk.content # original.choices[0].delta.content
 
 ### Extraction
 
-Often you want to extract structured information into a format like JSON. The [`extract`](../api/chat/models.md#mirascope.chat.models.OpenAIChat.extract) method makes this extremely easy by extracting the information into a Pydantic `BaseModel` schema that you define:
+Often you want to extract structured information into a format like JSON. The [`extract`](../api/chat/models/openai_chat.md#mirascope.chat.models.openai_chat.OpenAIChat.extract) method makes this extremely easy by extracting the information into a Pydantic `BaseModel` schema that you define:
 
 ```python
 from mirascope import OpenAIChat

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "mirascope"
-version = "0.2.3"
-description = "The most pythonic LLM application building experience"
+version = "0.2.4"
+description = "LLM toolkit for lightning-fast, high-quality development"
 license = "MIT"
 authors = [
  "William Bakst <[email protected]>",
@@ -17,17 +17,10 @@ mirascope = 'mirascope.cli.commands:app'
 [tool.poetry.dependencies]
 python = ">=3.9,<3.13"
 pydantic = "^2.0.2"
-
-# A list of optional dependencies that are required for certain features
-typer = { version = "^0.9.0", optional = true, extras = ["all"] }
-Jinja2 = { version = "^3.1.3", optional = true }
-openai = { version = "^1.6.0", optional = true }
-docstring-parser = { version = "^0.15", optional = true }
-
-[tool.poetry.extras]
-cli = ["typer", "Jinja2"]
-openai = ["openai", "docstring-parser"]
-all = ["typer", "Jinja2", "openai", "docstring-parser"]
+typer = { version = "^0.9.0", extras = ["all"] }
+Jinja2 = "^3.1.3"
+openai = "^1.6.0"
+docstring-parser = "^0.15"
 
 [tool.poetry.group.dev.dependencies]
 mypy = "^1.6.1"