docs: added first docs page (moved from README), and markdown support

.github/workflows/docs.yml

@@ -19,7 +19,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v2
         with:
-          python-version: '3.x'
+          python-version: '3.11'
 
       - name: Install dependencies
         run: |
@@ -54,6 +54,7 @@ jobs:
       - name: Deploy to GitHub Pages
         uses: peaceiris/actions-gh-pages@v3
         with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
           publish_dir: ./docs/_build
           publish_branch: gh-pages
           destination_dir: docs

Makefile

@@ -22,4 +22,4 @@ precommit:
 	make lint
 
 docs:
-	make -C docs html
+	poetry run make -C docs html

README.md

@@ -42,10 +42,11 @@ A local alternative to ChatGPT's "Advanced Data Analysis" (previously "Code Inte
 - 🤖 Support for many models
   - Including GPT-4 and **any model that runs in llama.cpp**
 
-In progress:
+🚧 In progress:
 
-- 📝 Handles long contexts through summarization, truncation, and pinning. (🚧 WIP)
-- 💬 Optional web UI and API for conversations. (🚧 WIP)
+- 📝 Handle long contexts intelligently through summarization, truncation, and pinning.
+- 💬 Web UI and API for conversations.
+- 🌐 Browse, interact, and automate the web from the terminal.
 
 ## 🛠 Use Cases
 
@@ -95,26 +96,10 @@ gptme --server
 
 And browse to http://localhost:5000/ to see the web UI.
 
-### 🖥 Local Models
+## 📚 Documentation
 
-To run local models, you need to install and run the [llama-cpp-python][llama-cpp-python] server. To ensure you get the most out of your hardware, make sure you build it with [the appropriate hardware acceleration][hwaccel].
+For more information, see the [documentation](https://erikbjare.github.io/gptme/docs/).
 
-For macOS, you can find detailed instructions [here][metal].
-
-I recommend the WizardCoder-Python models.
-
-[llama-cpp-python]: https://github.com/abetlen/llama-cpp-python
-[hwaccel]: https://github.com/abetlen/llama-cpp-python#installation-with-hardware-acceleration
-[metal]: https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md
-
-```sh
-MODEL=~/ML/wizardcoder-python-13b-v1.0.Q4_K_M.gguf
-poetry run python -m llama_cpp.server --model $MODEL --n_gpu_layers 1  # Use `--n_gpu_layer 1` if you have a M1/M2 chip
-
-# Now, to use it:
-export OPENAI_API_BASE="http://localhost:8000/v1"
-gptme --llm llama
-```
 
 ## 🛠 Usage
 

docs/conf.py

@@ -13,7 +13,8 @@
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-extensions = []
+extensions = ['myst_parser']
+
 
 templates_path = ['_templates']
 exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']

docs/index.rst

@@ -10,6 +10,8 @@ Welcome to gptme's documentation!
    :maxdepth: 2
    :caption: Contents:
 
+   local-models
+
 
 
 Indices and tables

docs/local-models.md

@@ -0,0 +1,22 @@
+🖥 Local Models
+===============
+
+To run gptme with local models, you need to install and run the [llama-cpp-python][llama-cpp-python] server. To ensure you get the most out of your hardware, make sure you build it with [the appropriate hardware acceleration][hwaccel].
+
+For macOS, you can find detailed instructions [here][metal].
+
+I recommend the WizardCoder-Python models.
+
+[llama-cpp-python]: https://github.com/abetlen/llama-cpp-python
+[hwaccel]: https://github.com/abetlen/llama-cpp-python#installation-with-hardware-acceleration
+[metal]: https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md
+
+```sh
+MODEL=~/ML/wizardcoder-python-13b-v1.0.Q4_K_M.gguf
+poetry run python -m llama_cpp.server --model $MODEL --n_gpu_layers 1  # Use `--n_gpu_layer 1` if you have a M1/M2 chip
+
+# Now, to use it:
+export OPENAI_API_BASE="http://localhost:8000/v1"
+gptme --llm local
+```
+

pyproject.toml

@@ -43,6 +43,7 @@ mypy = "*"
 ruff = "*"
 black = "*"
 sphinx = "^7.2.6"
+myst-parser = "^2.0.0"
 
 [tool.poetry.extras]
 server = ["llama-cpp-python", "flask"]