From 041b65d842e5a517e9a9160e8d37421136999576 Mon Sep 17 00:00:00 2001
From: reibs <areibman@gmail.com>
Date: Thu, 22 Feb 2024 15:07:44 -0800
Subject: [PATCH] update implementaiton notebook

---
 Example.ipynb        | 327 +++++++++++++++++++++++++++++++++++++++++++
 implementation.ipynb | 192 -------------------------
 jaiqu/__init__.py    |  10 --
 3 files changed, 327 insertions(+), 202 deletions(-)
 create mode 100644 Example.ipynb
 delete mode 100644 implementation.ipynb

diff --git a/Example.ipynb b/Example.ipynb
new file mode 100644
index 0000000..723dd09
--- /dev/null
+++ b/Example.ipynb
@@ -0,0 +1,327 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import jq\n",
+    "from jaiqu import validate_schema, translate_schema"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Desired data format \n",
+    "\n",
+    "Create a `jsonschema` dictionary for the format of data you want. Data extracted from your input will be extracted into this format."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "schema = {\n",
+    "    \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"id\": {\n",
+    "            \"type\": [\"string\", \"null\"],\n",
+    "            \"description\": \"A unique identifier for the record.\"\n",
+    "        },\n",
+    "        \"date\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"A string describing the date.\"\n",
+    "        },\n",
+    "        \"model\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"A text field representing the model used.\"\n",
+    "        }\n",
+    "    },\n",
+    "    \"required\": [\n",
+    "        \"id\",\n",
+    "        \"date\"\n",
+    "    ]\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sample input data\n",
+    "Provoide an input JSON dictionary containing the data you want to extract."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input_json = {\n",
+    "    \"call.id\": \"123\",\n",
+    "    \"datetime\": \"2022-01-01\",\n",
+    "    \"timestamp\": 1640995200,\n",
+    "    \"Address\": \"123 Main St\",\n",
+    "    \"user\": {\n",
+    "        \"name\": \"John Doe\",\n",
+    "        \"age\": 30,\n",
+    "        \"contact\": \"john@email.com\"\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### (Optional) Create hints\n",
+    "The jaiqu agent may not know certain concepts. For example, you might want to have some keys interpreted a certain way (i.e. interpret \"contact\" as \"email\"). For tricky interpretations, create hints."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "key_hints = \"We are processing outputs of an containing an id and a date of a user.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "16260aec353145dbb4055821841a64aa",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validating schema:   0%|          | 0/3 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "schema_properties, valid = validate_schema(input_json, schema, key_hints)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Verify schema\n",
+    "Verify the input JSON contains the keys and values requested in your schema"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Schema is valid: True\n",
+      "----------\n",
+      "{\n",
+      "  \"id\": {\n",
+      "    \"identified\": true,\n",
+      "    \"key\": \"call.id\",\n",
+      "    \"message\": \"\\\"call.id\\\" | \\\"id\\\" : Even though the names aren't exactly the same, we can infer that both fields aim to serve as identifiers. The embedded '.' in the key could imply a nested property or just a unique notation. Let's consider the likelihood that both fields are for unique identification which aligns with the intended role of \\\"id\\\". Also, looking at the type defined allows string or null which is compatible with the value provided. Extracted key: `call.id`.\",\n",
+      "    \"type\": [\n",
+      "      \"string\",\n",
+      "      \"null\"\n",
+      "    ],\n",
+      "    \"description\": \"A unique identifier for the record.\",\n",
+      "    \"required\": true\n",
+      "  },\n",
+      "  \"date\": {\n",
+      "    \"identified\": true,\n",
+      "    \"key\": \"datetime\",\n",
+      "    \"message\": \"\\\"date\\\" | \\\"datetime\\\" : The field names differ, but \\\"datetime\\\" could potentially contain the date information. Furthermore, the description of \\\"date\\\" suggests it's a string describing the date, which matches the type and content of the \\\"datetime\\\" field. Therefore we can extract the key: `datetime`.\",\n",
+      "    \"type\": \"string\",\n",
+      "    \"description\": \"A string describing the date.\",\n",
+      "    \"required\": true\n",
+      "  },\n",
+      "  \"model\": {\n",
+      "    \"identified\": false,\n",
+      "    \"key\": null,\n",
+      "    \"message\": \"\\\"model\\\" | None: There are no fields in the provided schema that match 'model' or imply a text field representing the model used. Extracted key: `None`\",\n",
+      "    \"type\": \"string\",\n",
+      "    \"description\": \"A text field representing the model used.\",\n",
+      "    \"required\": false\n",
+      "  }\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('Schema is valid:',valid)\n",
+    "print('-'*10)\n",
+    "print(json.dumps(schema_properties, indent=2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "58e46f7bc96c48cba50d4a78ccc4cd65",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validating schema:   0%|          | 0/3 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "219652ce841045bdbedf4032e5737faf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Translating schema:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "465972d7466f48dca0e07ff12688f981",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Retry attempts:   0%|          | 0/20 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "639d101d443c4805a34c269b1a36d0f6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation attempts:   0%|          | 0/20 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "jq_query = translate_schema(input_json, schema, key_hints=key_hints, max_retries=20)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Finalized jq query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'{ \"id\": (.\"call.id\"? // \"None\"), \"date\": (.datetime? // null) }'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "jq_query"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Check the jq query results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'id': '123', 'date': '2022-01-01'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = jq.compile(jq_query).input(input_json).all()\n",
+    "print(jq.compile(jq_query).input(input_json).all())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/implementation.ipynb b/implementation.ipynb
deleted file mode 100644
index 1cb0e89..0000000
--- a/implementation.ipynb
+++ /dev/null
@@ -1,192 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Requirement already satisfied: jq==1.6.0 in ./env/lib/python3.11/site-packages (from -r requirements.txt (line 1)) (1.6.0)\n",
-      "Collecting openai<2.0.0,>=1.12.0 (from -r requirements.txt (line 2))\n",
-      "  Using cached openai-1.12.0-py3-none-any.whl.metadata (18 kB)\n",
-      "Collecting jsonschema==4.21.1 (from -r requirements.txt (line 3))\n",
-      "  Using cached jsonschema-4.21.1-py3-none-any.whl.metadata (7.8 kB)\n",
-      "Requirement already satisfied: attrs>=22.2.0 in ./env/lib/python3.11/site-packages (from jsonschema==4.21.1->-r requirements.txt (line 3)) (23.2.0)\n",
-      "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in ./env/lib/python3.11/site-packages (from jsonschema==4.21.1->-r requirements.txt (line 3)) (2023.12.1)\n",
-      "Requirement already satisfied: referencing>=0.28.4 in ./env/lib/python3.11/site-packages (from jsonschema==4.21.1->-r requirements.txt (line 3)) (0.33.0)\n",
-      "Requirement already satisfied: rpds-py>=0.7.1 in ./env/lib/python3.11/site-packages (from jsonschema==4.21.1->-r requirements.txt (line 3)) (0.18.0)\n",
-      "Requirement already satisfied: anyio<5,>=3.5.0 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (4.3.0)\n",
-      "Requirement already satisfied: distro<2,>=1.7.0 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (1.9.0)\n",
-      "Requirement already satisfied: httpx<1,>=0.23.0 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (0.27.0)\n",
-      "Requirement already satisfied: pydantic<3,>=1.9.0 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (2.6.1)\n",
-      "Requirement already satisfied: sniffio in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (1.3.0)\n",
-      "Requirement already satisfied: tqdm>4 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (4.66.2)\n",
-      "Requirement already satisfied: typing-extensions<5,>=4.7 in ./env/lib/python3.11/site-packages (from openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (4.9.0)\n",
-      "Requirement already satisfied: idna>=2.8 in ./env/lib/python3.11/site-packages (from anyio<5,>=3.5.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (3.6)\n",
-      "Requirement already satisfied: certifi in ./env/lib/python3.11/site-packages (from httpx<1,>=0.23.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (2024.2.2)\n",
-      "Requirement already satisfied: httpcore==1.* in ./env/lib/python3.11/site-packages (from httpx<1,>=0.23.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (1.0.4)\n",
-      "Requirement already satisfied: h11<0.15,>=0.13 in ./env/lib/python3.11/site-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (0.14.0)\n",
-      "Requirement already satisfied: annotated-types>=0.4.0 in ./env/lib/python3.11/site-packages (from pydantic<3,>=1.9.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (0.6.0)\n",
-      "Requirement already satisfied: pydantic-core==2.16.2 in ./env/lib/python3.11/site-packages (from pydantic<3,>=1.9.0->openai<2.0.0,>=1.12.0->-r requirements.txt (line 2)) (2.16.2)\n",
-      "Using cached jsonschema-4.21.1-py3-none-any.whl (85 kB)\n",
-      "Using cached openai-1.12.0-py3-none-any.whl (226 kB)\n",
-      "Installing collected packages: openai, jsonschema\n",
-      "Successfully installed jsonschema-4.21.1 openai-1.12.0\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Requirement already satisfied: jaiqu in ./env/lib/python3.11/site-packages (0.0.1)\n",
-      "Requirement already satisfied: jq==1.6.0 in ./env/lib/python3.11/site-packages (from jaiqu) (1.6.0)\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/howardgil/Desktop/agentops/Jaiqu/env/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "!pip install -r requirements.txt\n",
-    "!pip install jaiqu\n",
-    "\n",
-    "#TODO update so that validate_schema is available on init\n",
-    "#TODO from jaiqu import validate_schema, translate_schema\n",
-    "from jaiqu.jaiqu import validate_schema, translate_schema\n",
-    "from jaiqu import JaiQu\n",
-    "JaiQu.init(openai_api_key=\"<YOUR_OPENAI_API_KEY>\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# !pip uninstall openai\n",
-    "# !pip uninstall jsonschema"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# TODO: Get from files\n",
-    "# Desired data format \n",
-    "schema = {\n",
-    "    \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n",
-    "    \"type\": \"object\",\n",
-    "    \"properties\": {\n",
-    "        \"id\": {\n",
-    "            \"type\": [\"string\", \"null\"],\n",
-    "            \"description\": \"A unique identifier for the record.\"\n",
-    "        },\n",
-    "        \"date\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"A string describing the date.\"\n",
-    "        },\n",
-    "        \"model\": {\n",
-    "            \"type\": \"string\",\n",
-    "            \"description\": \"A text field representing the model used.\"\n",
-    "        }\n",
-    "    },\n",
-    "    \"required\": [\n",
-    "        \"id\",\n",
-    "        \"date\"\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# Provided data\n",
-    "input_json = {\n",
-    "    \"call.id\": \"123\",\n",
-    "    \"datetime\": \"2022-01-01\",\n",
-    "    \"timestamp\": 1640995200,\n",
-    "    \"Address\": \"123 Main St\",\n",
-    "    \"user\": {\n",
-    "        \"name\": \"John Doe\",\n",
-    "        \"age\": 30,\n",
-    "        \"contact\": \"john@email.com\"\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "# (Optional) Create hints so the agent knows what to look for in the input\n",
-    "key_hints=\"We are processing outputs of an containing an id, a date, and a model. All the required fields should be present in this input, but the names might be different.\"\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Validating schema:   0%|          | 0/3 [00:00<?, ?it/s, Key: id]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Validating schema: 100%|██████████| 3/3 [00:10<00:00,  3.52s/it, Key: model]"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'id': {'identified': True, 'key': 'call.id', 'message': '\"Id\" | \"call.id\" : Although the field names are not identical, \"call.id\" implies an identifier related to the \"call\", which contextually could be equated to the unique identifier \\'id\\'. Furthermore, the desired type \\'string\\' also matches. Extracted key: `call.id`.', 'type': ['string', 'null'], 'description': 'A unique identifier for the record.', 'required': True}, 'date': {'identified': True, 'key': 'datetime', 'message': '\"date\" | \"datetime\": The field name is different. However, considering its type and description \\'A string describing the date\\', and also the fact that `datetime` in the provided schema contains a date string, makes them conceptually similar. Extracted key: `datetime`', 'type': 'string', 'description': 'A string describing the date.', 'required': True}, 'model': {'identified': False, 'key': None, 'message': '\"model\" | None: There\\'s no key in the provided schema that matches or could be inferred to represent the \\'model\\'. Extracted key: `None` \\n\\nAlthough the hint suggested we are looking for a model, none of the keys in the schema seem to represent this concept. Thus, it can\\'t be determined that the \\'model\\' field is present in the schema.', 'type': 'string', 'description': 'A text field representing the model used.', 'required': False}}\n",
-      "True\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "schema_properties, valid = validate_schema(input_json, schema, key_hints)\n",
-    "# TODO REMOVE jaiqu from schema_properties, valid = validate_schema(input_json, schema, key_hints)\n",
-    "\n",
-    "print(schema_properties)\n",
-    "print(valid)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "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": "3.11.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/jaiqu/__init__.py b/jaiqu/__init__.py
index 654102c..5741c0e 100644
--- a/jaiqu/__init__.py
+++ b/jaiqu/__init__.py
@@ -1,11 +1 @@
-from openai import OpenAI
 from .jaiqu import validate_schema, translate_schema
-
-
-class LLM:
-    openai_client = None
-
-    @classmethod
-    def init(cls, openai_api_key: str):
-        if cls.openai_client is None:
-            cls.openai_client = OpenAI(api_key=openai_api_key)