move docs stuff to /docs

Makefile

@@ -44,9 +44,9 @@ full:
 	poetry install --all-extras
 
 docs-gen:
-	poetry run python ./docs/pydocs/generate_pydocs.py
-	cp -r docs docs-build
-	poetry run nbdoc_build --force_all True --srcdir ./docs-build
+	poetry run python ./docs/docs/pydocs/generate_pydocs.py
+	cp -r docs/docs docs/docs-build
+	poetry run nbdoc_build --force_all True --srcdir ./docs/docs-build
 
 self-install:
 	pip install -e .

docs/concepts/async_streaming.ipynb → docs/docs/concepts/async_streaming.ipynb

@@ -22,7 +22,6 @@
     "# Few imports and global variables\n",
     "from rich import print\n",
     "import guardrails as gd\n",
-    "import litellm\n",
     "from IPython.display import clear_output\n",
     "import time"
    ]
@@ -86,10 +85,7 @@
     "# Wrap the litellm OpenAI API call with the `guard` object\n",
     "raw_llm_output, validated_output, *rest = await guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",
-    "    messages=[{\n",
-    "        \"role\": \"system\",\n",
-    "        \"content\": prompt\n",
-    "    }],\n",
+    "    messages=[{\"role\": \"system\", \"content\": prompt}],\n",
     "    max_tokens=1024,\n",
     "    temperature=0.3,\n",
     ")"
@@ -249,10 +245,7 @@
     "# Wrap the litellm OpenAI API call with the `guard` object\n",
     "fragment_generator = await guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",
-    "    messages=[{\n",
-    "        \"role\": \"user\",\n",
-    "        \"content\": prompt\n",
-    "    }],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "    max_tokens=1024,\n",
     "    temperature=0,\n",
     "    stream=True,\n",

docs/concepts/ml_based_validators.ipynb → docs/docs/concepts/ml_based_validators.ipynb

@@ -38,7 +38,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from guardrails import Guard\n"
+    "from guardrails import Guard"
    ]
   },
   {
@@ -70,10 +70,7 @@
    "source": [
     "from guardrails.hub import RegexMatch\n",
     "\n",
-    "guard = Guard().use(\n",
-    "    RegexMatch, \n",
-    "    regex=r\"^[a-zA-Z0-9_]+$\"\n",
-    ")\n",
+    "guard = Guard().use(RegexMatch, regex=r\"^[a-zA-Z0-9_]+$\")\n",
     "\n",
     "result = guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",
@@ -101,10 +98,8 @@
    "outputs": [],
    "source": [
     "from guardrails.hub import CompetitorCheck\n",
-    "guard = Guard().use(\n",
-    "    CompetitorCheck, \n",
-    "    [\"Apple\"]\n",
-    ")\n",
+    "\n",
+    "guard = Guard().use(CompetitorCheck, [\"Apple\"])\n",
     "\n",
     "result = guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",

docs/concepts/remote_validation_inference.ipynb → docs/docs/concepts/remote_validation_inference.ipynb

@@ -77,9 +77,7 @@
     "from guardrails import Guard\n",
     "from guardrails.hub import ToxicLanguage\n",
     "\n",
-    "guard = Guard().use(\n",
-    "    ToxicLanguage()\n",
-    ")"
+    "guard = Guard().use(ToxicLanguage())"
    ]
   },
   {
@@ -109,12 +107,11 @@
     ")\n",
     "\n",
     "\n",
-    "\n",
     "accumulated_output = \"\"\n",
     "for op in fragment_generator:\n",
     "    clear_output()\n",
     "    accumulated_output += op.validated_output\n",
-    "    display(accumulated_output)\n"
+    "    display(accumulated_output)"
    ]
   },
   {
@@ -161,14 +158,15 @@
    "outputs": [],
    "source": [
     "from guardrails import Guard, install\n",
+    "\n",
     "try:\n",
     "    from guardrails.hub import ToxicLanguage\n",
     "except ImportError:\n",
     "    install(\"hub://guardrails/toxic_language\", install_local_models=True)\n",
     "    from guardrails.hub import ToxicLanguage\n",
     "\n",
     "# uses validator locally.\n",
-    "guard.use(ToxicLanguage(use_local=True))\n"
+    "guard.use(ToxicLanguage(use_local=True))"
    ]
   },
   {

docs/concepts/streaming.ipynb → docs/docs/concepts/streaming.ipynb

@@ -25,7 +25,6 @@
    "source": [
     "from rich import print\n",
     "import guardrails as gd\n",
-    "import litellm\n",
     "from IPython.display import clear_output\n",
     "import time"
    ]
@@ -44,6 +43,7 @@
    "outputs": [],
    "source": [
     "from guardrails.hub import CompetitorCheck\n",
+    "\n",
     "prompt = \"Tell me about the Apple Iphone\"\n",
     "\n",
     "guard = gd.Guard().use(CompetitorCheck, [\"Apple\"])"

docs/concepts/streaming_structured_data.ipynb → docs/docs/concepts/streaming_structured_data.ipynb

@@ -16,7 +16,6 @@
     "# Few imports and global variables\n",
     "from rich import print\n",
     "import guardrails as gd\n",
-    "import litellm\n",
     "from IPython.display import clear_output\n",
     "import time"
    ]
@@ -43,7 +42,7 @@
     "    gd.install(\"hub://guardrails/uppercase\")\n",
     "    gd.install(\"hub://guardrails/lowercase\")\n",
     "    gd.install(\"hub://guardrails/one_line\")\n",
-    "    from guardrails.hub import LowerCase, UpperCase, ValidRange, OneLine\n"
+    "    from guardrails.hub import LowerCase, UpperCase, ValidRange, OneLine"
    ]
   },
   {
@@ -195,7 +194,7 @@
     "# Wrap the litellm OpenAI API call with the `guard` object\n",
     "raw_llm_output, validated_output, *rest = guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",
-    "    messages=[{\"role\":\"user\", \"content\":prompt}],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "    prompt_params={\"doctors_notes\": doctors_notes},\n",
     "    max_tokens=1024,\n",
     "    temperature=0.3,\n",
@@ -531,7 +530,7 @@
     "# Wrap the litellm OpenAI API call with the `guard` object\n",
     "fragment_generator = guard(\n",
     "    model=\"gpt-3.5-turbo\",\n",
-    "    messages=[{\"role\":\"user\", \"content\":prompt}],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "    prompt_params={\"doctors_notes\": doctors_notes},\n",
     "    max_tokens=1024,\n",
     "    temperature=0,\n",
@@ -828,7 +827,7 @@
     "        OneLine(on_fail=\"fix\"),\n",
     "    ],\n",
     "    description=\"testmeout\",\n",
-    "    messages=[{\"role\":\"user\", \"content\": prompt}],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     ")"
    ]
   },

docs/examples/bug_free_python_code.ipynb → docs/docs/examples/bug_free_python_code.ipynb

@@ -125,12 +125,9 @@
     "\n",
     "response = guard(\n",
     "    model=\"gpt-4o\",\n",
-    "    messages=[{\n",
-    "        \"role\": \"user\",\n",
-    "        \"content\": prompt\n",
-    "    }],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "    prompt_params={\"leetcode_problem\": leetcode_problem},\n",
-    "    temperature=0\n",
+    "    temperature=0,\n",
     ")\n",
     "\n",
     "print(response)"
@@ -206,7 +203,7 @@
     "try:\n",
     "    exec(response.validated_output)\n",
     "    print(\"Success!\")\n",
-    "except Exception as e:\n",
+    "except Exception:\n",
     "    print(\"Failed!\")"
    ]
   }

docs/examples/chatbot.ipynb → docs/docs/examples/chatbot.ipynb

@@ -132,7 +132,7 @@
     "from guardrails.hub import ProfanityFree, ToxicLanguage\n",
     "\n",
     "guard = Guard()\n",
-    "guard.name = 'ChatBotGuard'\n",
+    "guard.name = \"ChatBotGuard\"\n",
     "guard.use_many(ProfanityFree(), ToxicLanguage())"
    ]
   },
@@ -151,15 +151,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "base_message ={\n",
-    "        \"role\": \"system\",\n",
-    "        \"content\": \"\"\"You are a helpful assistant. \n",
+    "base_message = {\n",
+    "    \"role\": \"system\",\n",
+    "    \"content\": \"\"\"You are a helpful assistant. \n",
     "\n",
     "        Use the document provided to answer the user's question.\n",
     "\n",
     "        ${document}\n",
-    "        \"\"\"\n",
-    "    }"
+    "        \"\"\",\n",
+    "}"
    ]
   },
   {
@@ -182,13 +182,15 @@
     "\n",
     "import gradio as gr\n",
     "\n",
+    "\n",
     "def history_to_messages(history):\n",
     "    messages = [base_message]\n",
     "    for message in history:\n",
-    "            messages.append({\"role\": \"user\", \"content\": message[0]})\n",
-    "            messages.append({\"role\": \"assistant\", \"content\": message[1]})\n",
+    "        messages.append({\"role\": \"user\", \"content\": message[0]})\n",
+    "        messages.append({\"role\": \"assistant\", \"content\": message[1]})\n",
     "    return messages\n",
     "\n",
+    "\n",
     "def random_response(message, history):\n",
     "    messages = history_to_messages(history)\n",
     "    messages.append({\"role\": \"user\", \"content\": message})\n",
@@ -205,6 +207,7 @@
     "        return \"I'm sorry there was a problem, I can't answer that question.\"\n",
     "    return response.validated_output\n",
     "\n",
+    "\n",
     "gr.ChatInterface(random_response).launch()"
    ]
   },

docs/examples/competitors_check.ipynb → docs/docs/examples/competitors_check.ipynb

@@ -82,7 +82,7 @@
     "    \"JP Morgan\",\n",
     "    \"JP Morgan Chase\",\n",
     "    \"JPMorgan Chase\",\n",
-    "    \"Chase\" \"M1 Finance\",\n",
+    "    \"ChaseM1 Finance\",\n",
     "    \"Stash Financial Incorporated\",\n",
     "    \"Stash\",\n",
     "    \"Tastytrade Incorporated\",\n",
@@ -215,9 +215,7 @@
    ],
    "source": [
     "# Create the Guard with the CompetitorCheck Validator\n",
-    "guard = gd.Guard().use(\n",
-    "    CompetitorCheck(competitors=competitors_list, on_fail=\"fix\")\n",
-    ")\n",
+    "guard = gd.Guard().use(CompetitorCheck(competitors=competitors_list, on_fail=\"fix\"))\n",
     "\n",
     "# Test with a given text\n",
     "output = guard.parse(\n",

docs/examples/constrained_decoding.ipynb → docs/docs/examples/constrained_decoding.ipynb

@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -63,25 +63,41 @@
     "from guardrails import Guard\n",
     "from pydantic import BaseModel\n",
     "\n",
+    "# JSONFormer is only compatible with HF Pipelines and HF Models:\n",
+    "from transformers import pipeline\n",
+    "\n",
+    "\n",
     "class Dog(BaseModel):\n",
     "    name: str\n",
     "    color: str\n",
     "    weight_kg: float\n",
     "\n",
+    "\n",
     "class NewFriends(BaseModel):\n",
     "    dogs: list[Dog]\n",
     "\n",
+    "\n",
     "guard = Guard.for_pydantic(NewFriends, output_formatter=\"jsonformer\")\n",
     "\n",
-    "# JSONFormer is only compatible with HF Pipelines and HF Models:\n",
-    "from transformers import pipeline\n",
+    "\n",
     "tiny_llama_pipeline = pipeline(\"text-generation\", \"TinyLlama/TinyLlama-1.1B-Chat-v1.0\")\n",
     "\n",
     "# Inference is straightforward:\n",
-    "response = guard(tiny_llama_pipeline, messages=[{\"role\":\"user\", \"content\":\"Please enjoy this list of good dogs:\"}])\n",
-    "\n",
+    "response = guard(\n",
+    "    tiny_llama_pipeline,\n",
+    "    messages=[{\"role\": \"user\", \"content\": \"Please enjoy this list of good dogs:\"}],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "# `out` is a dict.  Format it as JSON for readability:\n",
     "import json\n",
+    "\n",
     "print(json.dumps(response.validated_output, indent=2))"
    ]
   }

docs/examples/extracting_entities.ipynb → docs/docs/examples/extracting_entities.ipynb

@@ -151,18 +151,27 @@
     "${gr.complete_xml_suffix_v2}\n",
     "\"\"\"\n",
     "\n",
+    "\n",
     "class Fee(BaseModel):\n",
     "    name: str = Field(validators=[LowerCase(on_fail=\"fix\"), TwoWords(on_fail=\"reask\")])\n",
     "    explanation: str = Field(validators=[OneLine(on_fail=\"noop\")])\n",
     "    value: float = Field(description=\"The fee amount in USD or as a percentage.\")\n",
     "\n",
+    "\n",
     "class AccountFee(BaseModel):\n",
     "    account_type: str = Field(validators=[LowerCase(on_fail=\"fix\")])\n",
-    "    rate: float = Field(description=\"The annual percentage rate (APR) for the account type.\")\n",
+    "    rate: float = Field(\n",
+    "        description=\"The annual percentage rate (APR) for the account type.\"\n",
+    "    )\n",
+    "\n",
     "\n",
     "class CreditCardAgreement(BaseModel):\n",
-    "    fees: list[Fee] = Field(description=\"What fees and charges are associated with my account?\")\n",
-    "    interest_rates: list[AccountFee] = Field(description=\"What are the interest rates offered by the bank on different kinds of accounts and products?\")"
+    "    fees: list[Fee] = Field(\n",
+    "        description=\"What fees and charges are associated with my account?\"\n",
+    "    )\n",
+    "    interest_rates: list[AccountFee] = Field(\n",
+    "        description=\"What are the interest rates offered by the bank on different kinds of accounts and products?\"\n",
+    "    )"
    ]
   },
   {
@@ -228,11 +237,11 @@
     "# os.environ[\"OPENAI_API_KEY\"] = \"YOUR_API_KEY\"\n",
     "\n",
     "raw_llm_response, validated_response, *rest = guard(\n",
-    "    messages=[{\"role\":\"user\", \"content\": prompt}],\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "    prompt_params={\"document\": content[:6000]},\n",
     "    model=\"gpt-4o-mini\",\n",
     "    max_tokens=2048,\n",
-    "    temperature=0\n",
+    "    temperature=0,\n",
     ")"
    ]
   },