📜 update docs

shroominic · Oct 22, 2023 · 2fbd51c · 2fbd51c
1 parent 2789429
commit 2fbd51c
Show file tree

Hide file tree

Showing 15 changed files with 51 additions and 85 deletions.
diff --git a/docs/bitcoin_chart.md b/docs/bitcoin_chart.md
@@ -1,4 +1,5 @@
 # Bitcoin Chart
+
 This example creates a CodeInterpreterSession and generates a response to plot the bitcoin chart for year 2023:
 
 ```python

diff --git a/docs/code_interpreter_response.md b/docs/code_interpreter_response.md
@@ -1,4 +1,5 @@
 # CodeInterpreterResponse
+
 The CodeInterpreterResponse contains the AI agent's response.
 
 It contains:

diff --git a/docs/code_interpreter_session.md b/docs/code_interpreter_session.md
@@ -1,4 +1,5 @@
 # CodeInterpreterSession
+
 The CodeInterpreterSession is the main class that manages a conversational session between the user and AI agent. It handles starting, stopping and checking status of the secure isolated code execution environment.
 
 Key responsibilities:
@@ -17,7 +18,6 @@ It provides methods like:
 - `log()`: Log messages
 - `show_code` - Callback to print code before running.
 
-
 The response generation happens through a pipeline:
 
 1. User input is parsed

diff --git a/docs/codebox.md b/docs/codebox.md
@@ -1,4 +1,5 @@
 # CodeBox
+
 The CodeBox class provides the isolated secure environment for executing python code. It is used by the CodeInterpreterSession internally.
 
 It provides methods like:

diff --git a/docs/concepts_overview.md b/docs/concepts_overview.md
@@ -1,4 +1,5 @@
 # Concepts Overview
+
 | name | description |
 |-|-|
 | CodeInterpreterSession | Main class that manages a code execution session |

diff --git a/docs/deploy.md b/docs/deploy.md
@@ -1,9 +1,11 @@
 # Deployment
+
 CodeInterpreterAPI can be easily deployed to production using the CodeBox framework.
 
 ## Prerequisites
+
 - CodeBox API key
-  - Get your API key from [CodeBox](https://pay.codeboxapi.com/b/00g3e6dZX2fTg0gaEE) (get 70% with the code `BETA`)
+  - Get your API key from [CodeBox](https://pay.codeboxapi.com/b/00g3e6dZX2fTg0gaEE) (you get an email with the api-key)
 - CodeInterpreterAPI installed
   - `pip install codeinterpreterapi`
 
@@ -17,36 +19,6 @@ from codeinterpreterapi import settings
 settings.CODEBOX_API_KEY = "sk-..."
 ```
 
-## Starting a Session
-
-To start a code interpreter session using CodeBox:
-
-```python
-from uuid import uuid4
-from codeinterpreterapi import CodeInterpreterSession
-
-session_id = uuid4()
-
-session = CodeInterpreterSession.from_id(session_id)
-session.start()
-```
-
-The `session_id` allows restoring the session later after restarting the application.
-
-## Generating Responses
-
-With the session started, you can now generate responses like normal:
-
-```python
-response = session.generate_response(
-  "Plot a histogram of the iris dataset"
-)
-
-response.show()
-```
-
-This will execute the code securely using CodeBox.
-
 ## Stopping the Session
 
 Don't forget to stop the session when finished:
@@ -61,4 +33,4 @@ This will shutdown the CodeBox instance.
 
 - See the [CodeBox docs](https://codeboxapi.com/docs) for more details on deployment options.
 - Look at the [examples](https://github.com/shroominic/codebox-api/tree/main/examples) for more usage ideas.
-- Contact [Shroominic](https://twitter.com/shroominic) for assistance with scaling.
+- Contact [Shroominic](https://twitter.com/shroominic) for assistance with deployment.
diff --git a/docs/file.md b/docs/file.md
@@ -1,4 +1,5 @@
-# File
+# File Object
+
 The File class is used to represent files that are uploaded or downloaded during the session.
 
 It stores the filename and binary content of the file.

diff --git a/docs/index.md b/docs/index.md
@@ -1,31 +1,10 @@
-# CodeInterpreterAPI Documentation
+# Welcome
 
-CodeInterpreterAPI is a Python-based API designed give LLM Agents access to python and execute code. It provides a session-based conversational chat interface and the agent framework with a tool for executing code in a secure and isolated environment.
+This project provides a LangChain implementation of the ChatGPT Code Interpreter. It allows you to have a back and forth chat with the AI assistant to get it to help with programming tasks, data analysis, and more. You can run everything local except the LLM using your own OpenAI API Key.
 
-## Key Classes
+Some key features:
 
-### CodeInterpreterSession
-
-This is the main class that manages a code execution session. It provides methods to start, stop, and check the status of the session. It also handles logging and file uploads for the session.
-
-#### Methods
-
-* `from_id(session_id: UUID, **kwargs) -> "CodeInterpreterSession"`: This class method creates a new session from a given UUID.
-* `start() -> SessionStatus`: This method starts the session.
-* `stop() -> SessionStatus`: This method stops the session.
-* `log(msg: str) -> None`: This method logs a message.
-
-### CodeBox
-
-This class represents the code execution environment. It provides methods to upload files, execute code, and check the status of the execution. For more information look into the codebox api documentation.
-
-## Usage
-
-To use this API, create a new `CodeInterpreterSession` and use the `start` method to start the session. You can then use the `generate_response_sync` method to generate an AI response and the `stop` method to stop the session. You can use the generate response method multiple times in a single session to have a conversation with the AI.
-
-## Contributing
-
-Contributions are welcome. Please make sure to write functional Python with full type hinting and only write needed and precise comments.
-
-(This file was half chatgpt generated and not complete - real docs coming soon!)
-TODO: Write real docs
+- Sandboxed execution of Python code snippets provided by the AI assistant using CodeBox. CodeBox is the simplest cloud infrastructure for your LLM Apps.
+- Automatic handling of file uploads/downloads
+- Support for stateful conversations with chat history
+- Extensible architecture to add custom tools and logic
diff --git a/docs/installation.md b/docs/installation.md
@@ -1,14 +1,6 @@
 # Installation
-## Install Dependencies
 
-To install, it's recommended to create a virtual environment (using `venv` in the example below):
-
-```bash
-python3 -m venv codeinterpreterenv
-source codeinterpreterenv/bin/activate
-```
-
-Then install the package:
+Install the package:
 
 ```bash
 pip install "codeinterpreterapi[all]"
@@ -18,18 +10,18 @@ Everything for local experiments are installed with the all extra. For deploymen
 
 ## Set Up Environment Variables
 
-
 You will also need to configure API keys for the AI model you want to use, either OpenAI, Anthropic, or Azure.
 
 For OpenAI, create a `.env` file with:
 
 ```bash
-OPENAI_API_KEY=sk-...
+OPENAI_API_KEY=sk-**********
 ```
-or export as an environment variable in your terminal:
+
+or export as an environment variable in your terminal before running your code:
 
 ```bash
-export OPENAI_API_KEY=your_openai_api_key
+export OPENAI_API_KEY=sk-**********
 ```
 
 For Azure, use:

diff --git a/docs/iris_dataset.md b/docs/iris_dataset.md
@@ -1,4 +1,5 @@
 # Analyzing the Iris Dataset
+
 ```python
 from codeinterpreterapi import CodeInterpreterSession, File
 

diff --git a/docs/streamlit_webapp.md b/docs/streamlit_webapp.md
@@ -1,4 +1,5 @@
 # Using the Streamlit Webapp
+
 The streamlit webapp allows interacting with the API through a GUI:
 
 ```bash

diff --git a/docs/usage.md b/docs/usage.md
@@ -1,4 +1,5 @@
 # Usage
+
 To create a session and generate a response:
 
 ```python

diff --git a/docs/user_request.md b/docs/user_request.md
@@ -1,4 +1,5 @@
 # UserRequest
+
 The UserRequest class represents the user input to the agent.
 
 It contains:

diff --git a/docs/welcome.md b/docs/welcome.md
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -1,4 +1,27 @@
-site_name: CodeInterpreterAPI - Docs
+site_name: CodeInterpreterAPI - Documentation
+site_author: Shroominic
+site_url: https://shroominic.github.io/codeinterpreter-api/
+repo_name: shroominic/codeinterpreter-api
+repo_url: https://github.com/shroominic/codeinterpreter-api/
+
+nav:
+  - 'Getting Started':
+    - 'Welcome': 'index.md'
+    - 'Installation': 'installation.md'
+    - 'Usage': 'usage.md'
+  - 'Code Interpreter':
+    - 'Overview': 'concepts_overview.md'
+    - 'Session': 'code_interpreter_session.md'
+    - 'CodeBox': 'codebox.md'
+    - 'File': 'file.md'
+    - 'Request': 'user_request.md'
+    - 'Response': 'code_interpreter_response.md'
+  - 'Deployment': 'deploy.md'
+  - 'Examples':
+    - 'Bitcoin Chart': 'bitcoin_chart.md'
+    - 'Iris Dataset': 'iris_dataset.md'
+    - 'Streamlit Webapp': 'streamlit_webapp.md'
+
 theme:
   name: material
   palette: