diff --git a/docs/docs/get-started/quick-tour-notebook/quick-tour.ipynb b/docs/docs/get-started/quick-tour-notebook/quick-tour.ipynb
new file mode 100644
index 00000000..299fc6cc
--- /dev/null
+++ b/docs/docs/get-started/quick-tour-notebook/quick-tour.ipynb
@@ -0,0 +1,518 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "57cUBU_kW8YI"
+ },
+ "source": [
+ "LaVague: Quick-tour guide
"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Installation\n",
+ "\n",
+ "We can install everything we need to get started with LaVague using our `setup.sh` script.\n",
+ "\n",
+ "We'll also download the config and instruction files we will use in this demo.\n",
+ "\n",
+ "> This downloads the webdriver needed to leverage Selenium to interact with the browser, as well as the LaVague package."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Run the LaVague setup script\n",
+ "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/setup.sh\n",
+ "!sudo bash setup.sh\n",
+ "\n",
+ "# Download files needed for demo to current repo\n",
+ "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/examples/configurations/api/openai_api.py\n",
+ "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/examples/instructions/huggingface.yaml"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### OpenAI API key\n",
+ "\n",
+ "By default, LaVague uses OpenAI GPT3.5 and an OpenAI light embedder. Please make sure you've set the `OPENAI_API_KEY` environment variable with your OpenAI key, or if you're running this in our Google Colab, set it in the command below."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "\n",
+ "os.environ['OPENAI_API_KEY'] = # ADD YOUR OPENAI KEY HERE"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### LaVague Launch\n",
+ "\n",
+ "Let's now run the `lavague [OPTIONS] launch` command!\n",
+ "\n",
+ "- The `--instructions` or `-i` option accepts a text file containing: the URL of the website we will interact with & the instructions for the actions we wish to automate\n",
+ "- The `--config` or `-c` option with a Python file which can be used to set a desired LLM, embedder etc.\n",
+ "\n",
+ "For more info on these, see the [customization guide](./customization.md)!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!lavague -i huggingface.yaml -c openai_api.py launch"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "You can now click on the public (if you are using Google Colab) or local URL to open your interactive LaVague demo.\n",
+ "\n",
+ "⚠️ You'll need to interact with this demo:\n",
+ "\n",
+ "1) Click on the URL textbox and press enter. This will show a screenshot of your inital page.\n",
+ "\n",
+ "![](\"https://raw.githubusercontent.com/lavague-ai/LaVague/main/docs/assets/launch_1_openai_py.png\")
\n",
+ "\n",
+ "2) Then select an instruction or write your own, and again click within the instruction textbox and press enter.\n",
+ "\n",
+ "At this point, your Python code leveraging Selenium is generated by the LLM & executed. You will see an updated image of the website after the code is executed.\n",
+ "\n",
+ "![](\"https://raw.githubusercontent.com/lavague-ai/LaVague/main/docs/assets/launch_2_openai_py.png\")
"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### LaVague Build\n",
+ "\n",
+ "We can use `lavague [OPTIONS] build` command to generate a file containing this automation code without launching an interactive demo."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!lavague -i huggingface.yaml -c openai_api.py build"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This creates a script in your current directory named `hf_openai_api_gen.py` - a combination of the two input file names separated by a `_` character with a `_gen` suffix.\n",
+ "\n",
+ "We can now inspect the code and execute it locally!\n",
+ "\n",
+ "![](\"https://raw.githubusercontent.com/lavague-ai/LaVague/main/docs/assets/build_openai_py.png\"/)
\n"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "If you have any further questions, join us on the LaVague Discord [here](https://discord.com/invite/SDxn9KpqX9)."
+ ]
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "gpuType": "T4",
+ "machine_shape": "hm",
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "0d9126c291a04e8fb1ce30a7103197d1": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "15c0d6723eba4298b61ddd67c1595f66": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_0d9126c291a04e8fb1ce30a7103197d1",
+ "max": 4,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_a36c6df55813490a9e0b42b67a698327",
+ "value": 4
+ }
+ },
+ "2600f072828a4abf8e8ed51cd64f2dc2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_984f401572a645f7861db035993c806b",
+ "placeholder": "",
+ "style": "IPY_MODEL_2ba0655ceb93417d859921bf08b5ec9d",
+ "value": "Loading checkpoint shards: 100%"
+ }
+ },
+ "2ba0655ceb93417d859921bf08b5ec9d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "398c2359c137457b94fe7ed7b8c4b939": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_2600f072828a4abf8e8ed51cd64f2dc2",
+ "IPY_MODEL_15c0d6723eba4298b61ddd67c1595f66",
+ "IPY_MODEL_d1a4215edd20433482d339c83c9d0060"
+ ],
+ "layout": "IPY_MODEL_c71a506bf63948c8bfb79b6811705de5"
+ }
+ },
+ "777ac9bad3974a2ab7062644bda6a3c6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "984f401572a645f7861db035993c806b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "a36c6df55813490a9e0b42b67a698327": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "c71a506bf63948c8bfb79b6811705de5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d1a4215edd20433482d339c83c9d0060": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ec5d092ea24946279f14f03570a48c98",
+ "placeholder": "",
+ "style": "IPY_MODEL_777ac9bad3974a2ab7062644bda6a3c6",
+ "value": " 4/4 [00:12<00:00, 2.89s/it]"
+ }
+ },
+ "ec5d092ea24946279f14f03570a48c98": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ }
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/docs/docs/get-started/quick-tour.ipynb b/docs/docs/get-started/quick-tour.ipynb
index 1bcc5d0f..4597c19d 100644
--- a/docs/docs/get-started/quick-tour.ipynb
+++ b/docs/docs/get-started/quick-tour.ipynb
@@ -6,11 +6,7 @@
"id": "57cUBU_kW8YI"
},
"source": [
- ""
+ "LaVague: Quick-tour guide
"
]
},
{
@@ -21,58 +17,21 @@
"In this quick tour we're going to show you how you can use LaVague to perform actions on web from text instructions 🤯\n",
"\n",
"We'll get you started with our two CLI commands:\n",
- "- `lavague [OPTIONS] launch`: Launch an interactive in-browser Gradio demo where you can test out instructing LaVague to perform actions on a website!\n",
- "- `lavague [OPTIONS] build`: Get the raw Python code generated by LaVague which you can then execute locally"
- ]
- },
- {
- "attachments": {},
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Installation\n",
+ "- `lavague launch`: Launch an interactive in-browser Gradio demo where you can test out instructing LaVague to perform actions on a website!\n",
+ "- `lavague build`: Get the raw Python code generated by LaVague which you can then execute locally\n",
"\n",
- "We can install everything we need to get started with LaVague using our `setup.sh` script.\n",
+ "**Pre-requisites:**\n",
+ "- We assume you have already installed LaVague & the necessary dependencies as outlined in our [installation guide](./setting-up-la-vague.md)\n",
+ "- If you are running the notebook locally, you will need Python (test on python>=3.8) and pip installed\n",
+ "- Our default demo uses the OpenAI API. You will need to have an OPENAI_API_KEY environment variable set in your local environment\n",
"\n",
- "We'll also download the config and instruction files we will use in this demo.\n",
+ "> For other integrations, see our [integrations](../integrations/home.md) section\n",
"\n",
- "> This downloads the webdriver needed to leverage Selenium to interact with the browser, as well as the LaVague package."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Run the LaVague setup script\n",
- "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/setup.sh\n",
- "!sudo bash setup.sh\n",
- "\n",
- "# Download files needed for demo to current repo\n",
- "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/examples/configurations/api/openai_api.py\n",
- "!wget https://raw.githubusercontent.com/lavague-ai/LaVague/main/examples/instructions/huggingface.yaml"
- ]
- },
- {
- "attachments": {},
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### OpenAI API key\n",
- "\n",
- "By default, LaVague uses OpenAI GPT3.5 and an OpenAI light embedder. Please make sure you've set the `OPENAI_API_KEY` environment variable with your OpenAI key, or if you're running this in our Google Colab, set it in the command below."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "import os\n",
- "\n",
- "os.environ['OPENAI_API_KEY'] = # ADD YOUR OPENAI KEY HERE"
+ "If you prefer to run this example as an end-to-end example with Google Colab, you can follow this link.\n",
+ ""
]
},
{
@@ -82,7 +41,7 @@
"source": [
"### LaVague Launch\n",
"\n",
- "Let's now run the `lavague [OPTIONS] launch` command!\n",
+ "Let's now run the `lavague launch` command!\n",
"\n",
"- The `--instructions` or `-i` option accepts a text file containing: the URL of the website we will interact with & the instructions for the actions we wish to automate\n",
"- The `--config` or `-c` option with a Python file which can be used to set a desired LLM, embedder etc.\n",
@@ -126,7 +85,7 @@
"source": [
"### LaVague Build\n",
"\n",
- "We can use `lavague [OPTIONS] build` command to generate a file containing this automation code without launching an interactive demo."
+ "We can use `lavague build` command to generate a file containing this automation code without launching an interactive demo."
]
},
{
diff --git a/docs/docs/integrations/azure-openai.ipynb b/docs/docs/integrations/api/azure-openai.ipynb
similarity index 99%
rename from docs/docs/integrations/azure-openai.ipynb
rename to docs/docs/integrations/api/azure-openai.ipynb
index 132cce55..bab4f7aa 100644
--- a/docs/docs/integrations/azure-openai.ipynb
+++ b/docs/docs/integrations/api/azure-openai.ipynb
@@ -9,7 +9,7 @@
"source": [
""
]
diff --git a/docs/docs/integrations/hugging-face-api.ipynb b/docs/docs/integrations/api/hugging-face.ipynb
similarity index 99%
rename from docs/docs/integrations/hugging-face-api.ipynb
rename to docs/docs/integrations/api/hugging-face.ipynb
index 72ad237a..cb79de72 100644
--- a/docs/docs/integrations/hugging-face-api.ipynb
+++ b/docs/docs/integrations/api/hugging-face.ipynb
@@ -8,8 +8,8 @@
},
"source": [
""
]
diff --git a/docs/docs/integrations/litellm.ipynb b/docs/docs/integrations/api/litellm.ipynb
similarity index 99%
rename from docs/docs/integrations/litellm.ipynb
rename to docs/docs/integrations/api/litellm.ipynb
index fb26a19a..8118b741 100644
--- a/docs/docs/integrations/litellm.ipynb
+++ b/docs/docs/integrations/api/litellm.ipynb
@@ -9,7 +9,7 @@
"source": [
""
]
diff --git a/docs/docs/integrations/openai.ipynb b/docs/docs/integrations/api/openai.ipynb
similarity index 99%
rename from docs/docs/integrations/openai.ipynb
rename to docs/docs/integrations/api/openai.ipynb
index 197228b3..69bcee02 100644
--- a/docs/docs/integrations/openai.ipynb
+++ b/docs/docs/integrations/api/openai.ipynb
@@ -9,7 +9,7 @@
"source": [
""
]
diff --git a/docs/docs/integrations/local-inference.ipynb b/docs/docs/integrations/local/local-inference.ipynb
similarity index 99%
rename from docs/docs/integrations/local-inference.ipynb
rename to docs/docs/integrations/local/local-inference.ipynb
index 5640bd68..67f18b90 100644
--- a/docs/docs/integrations/local-inference.ipynb
+++ b/docs/docs/integrations/local/local-inference.ipynb
@@ -8,8 +8,8 @@
},
"source": [
""
]
diff --git a/mkdocs.yml b/mkdocs.yml
index 3b5b33ea..deffc4b0 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -102,12 +102,14 @@ nav:
- 🤝 Integrations:
- Overview: 'docs/integrations/home.md'
- - Azure OpenAI: 'docs/integrations/azure-openai.ipynb'
- - HuggingFace API: 'docs/integrations/hugging-face-api.ipynb'
- - OpenAI: 'docs/integrations/openai.ipynb'
- - Local: 'docs/integrations/local-inference.ipynb'
- - Litellm: 'docs/integrations/litellm.ipynb'
-
+ - Api:
+ - Azure OpenAI: 'docs/integrations/api/azure-openai.ipynb'
+ - HuggingFace: 'docs/integrations/hugging-face-api.ipynb'
+ - OpenAI: 'docs/integrations/openai.ipynb'
+ - Litellm: 'docs/integrations/litellm.ipynb'
+ - Local:
+ - DeepSeek Coder: 'docs/integrations/local-inference.ipynb'
+
- ⚡ Advanced:
- Architecture: 'docs/get-started/architecture.md'
- Telemetry: 'docs/advanced/telemetry.md'
![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
\n",
- "