{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yC3of5RRdsny", "outputId": "d9baa889-7061-48c3-f4db-e91a19a59f15" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting langchain\n", " Downloading langchain-0.0.132-py3-none-any.whl (489 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m489.1/489.1 KB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting dataclasses-json<0.6.0,>=0.5.7\n", " Downloading dataclasses_json-0.5.7-py3-none-any.whl (25 kB)\n", "Collecting aiohttp<4.0.0,>=3.8.3\n", " Downloading aiohttp-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m24.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: PyYAML>=5.4.1 in /usr/local/lib/python3.9/dist-packages (from langchain) (6.0)\n", "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.22.4)\n", "Requirement already satisfied: SQLAlchemy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.4.47)\n", "Requirement already satisfied: pydantic<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.10.7)\n", "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.27.1)\n", "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (8.2.2)\n", "Collecting yarl<2.0,>=1.0\n", " Downloading yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (264 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 KB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting multidict<7.0,>=4.5\n", " Downloading multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 KB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting frozenlist>=1.1.1\n", " Downloading frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (158 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 KB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting aiosignal>=1.1.2\n", " Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", "Collecting async-timeout<5.0,>=4.0.0a3\n", " Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (22.2.0)\n", "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (2.0.12)\n", "Collecting marshmallow-enum<2.0.0,>=1.5.1\n", " Downloading marshmallow_enum-1.5.1-py2.py3-none-any.whl (4.2 kB)\n", "Collecting typing-inspect>=0.4.0\n", " Downloading typing_inspect-0.8.0-py3-none-any.whl (8.7 kB)\n", "Collecting marshmallow<4.0.0,>=3.3.0\n", " Downloading marshmallow-3.19.0-py3-none-any.whl (49 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.1/49.1 KB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic<2,>=1->langchain) (4.5.0)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (3.4)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (2022.12.7)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (1.26.15)\n", "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.9/dist-packages (from SQLAlchemy<2,>=1->langchain) (2.0.2)\n", "Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.9/dist-packages (from marshmallow<4.0.0,>=3.3.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (23.0)\n", "Collecting mypy-extensions>=0.3.0\n", " Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)\n", "Installing collected packages: mypy-extensions, multidict, marshmallow, frozenlist, async-timeout, yarl, typing-inspect, marshmallow-enum, aiosignal, dataclasses-json, aiohttp, langchain\n", "Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 dataclasses-json-0.5.7 frozenlist-1.3.3 langchain-0.0.132 marshmallow-3.19.0 marshmallow-enum-1.5.1 multidict-6.0.4 mypy-extensions-1.0.0 typing-inspect-0.8.0 yarl-1.8.2\n" ] } ], "source": [ "!pip install langchain" ] }, { "cell_type": "code", "source": [ "!pip install unstructured\n", "!pip install unstructured[local-inference]" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "teH1sHCZd3Wl", "outputId": "ab8180e2-ffe3-4c5c-d27b-976594d9ac22" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: unstructured in /usr/local/lib/python3.9/dist-packages (0.5.9)\n", "Requirement already satisfied: argilla in /usr/local/lib/python3.9/dist-packages (from unstructured) (1.5.1)\n", "Requirement already satisfied: openpyxl in /usr/local/lib/python3.9/dist-packages (from unstructured) (3.0.10)\n", "Requirement already satisfied: python-magic in /usr/local/lib/python3.9/dist-packages (from unstructured) (0.4.27)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from unstructured) (1.4.4)\n", "Requirement already satisfied: python-docx in /usr/local/lib/python3.9/dist-packages (from unstructured) (0.8.11)\n", "Requirement already satisfied: msg-parser in /usr/local/lib/python3.9/dist-packages (from unstructured) (1.2.0)\n", "Requirement already satisfied: nltk in /usr/local/lib/python3.9/dist-packages (from unstructured) (3.8.1)\n", "Requirement already satisfied: markdown in /usr/local/lib/python3.9/dist-packages (from unstructured) (3.4.3)\n", "Requirement already satisfied: lxml in /usr/local/lib/python3.9/dist-packages (from unstructured) (4.9.2)\n", "Requirement already satisfied: python-pptx in /usr/local/lib/python3.9/dist-packages (from unstructured) (0.6.21)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from unstructured) (2.27.1)\n", "Requirement already satisfied: pypandoc in /usr/local/lib/python3.9/dist-packages (from unstructured) (1.11)\n", "Requirement already satisfied: certifi>=2022.12.07 in /usr/local/lib/python3.9/dist-packages (from unstructured) (2022.12.7)\n", "Requirement already satisfied: pillow in /usr/local/lib/python3.9/dist-packages (from unstructured) (9.5.0)\n", "Requirement already satisfied: numpy<1.24.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (1.22.4)\n", "Requirement already satisfied: monotonic in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (1.6)\n", "Requirement already satisfied: wrapt<1.15,>=1.13 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (1.14.1)\n", "Requirement already satisfied: pydantic>=1.7.1 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (1.10.7)\n", "Requirement already satisfied: backoff in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (2.2.1)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (23.0)\n", "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (4.65.0)\n", "Requirement already satisfied: rich<=13.0.1 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (13.0.1)\n", "Requirement already satisfied: deprecated~=1.2.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (1.2.13)\n", "Requirement already satisfied: httpx<0.24,>=0.15 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured) (0.23.3)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->unstructured) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->unstructured) (2022.7.1)\n", "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.9/dist-packages (from markdown->unstructured) (6.1.0)\n", "Requirement already satisfied: olefile>=0.46 in /usr/local/lib/python3.9/dist-packages (from msg-parser->unstructured) (0.46)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured) (1.1.1)\n", "Requirement already satisfied: click in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured) (8.1.3)\n", "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured) (2022.10.31)\n", "Requirement already satisfied: et-xmlfile in /usr/local/lib/python3.9/dist-packages (from openpyxl->unstructured) (1.1.0)\n", "Requirement already satisfied: XlsxWriter>=0.5.7 in /usr/local/lib/python3.9/dist-packages (from python-pptx->unstructured) (3.0.9)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured) (1.26.15)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured) (3.4)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured) (2.0.12)\n", "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured) (0.16.3)\n", "Requirement already satisfied: sniffio in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured) (1.3.0)\n", "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured) (1.5.0)\n", "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/dist-packages (from importlib-metadata>=4.4->markdown->unstructured) (3.15.0)\n", "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic>=1.7.1->argilla->unstructured) (4.5.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->unstructured) (1.16.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.6.0 in /usr/local/lib/python3.9/dist-packages (from rich<=13.0.1->argilla->unstructured) (2.14.0)\n", "Requirement already satisfied: commonmark<0.10.0,>=0.9.0 in /usr/local/lib/python3.9/dist-packages (from rich<=13.0.1->argilla->unstructured) (0.9.1)\n", "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.9/dist-packages (from httpcore<0.17.0,>=0.15.0->httpx<0.24,>=0.15->argilla->unstructured) (3.6.2)\n", "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.9/dist-packages (from httpcore<0.17.0,>=0.15.0->httpx<0.24,>=0.15->argilla->unstructured) (0.14.0)\n", "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: unstructured[local-inference] in /usr/local/lib/python3.9/dist-packages (0.5.9)\n", "Requirement already satisfied: pillow in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (9.5.0)\n", "Requirement already satisfied: nltk in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (3.8.1)\n", "Requirement already satisfied: lxml in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (4.9.2)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (1.4.4)\n", "Requirement already satisfied: openpyxl in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (3.0.10)\n", "Requirement already satisfied: argilla in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (1.5.1)\n", "Requirement already satisfied: markdown in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (3.4.3)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (2.27.1)\n", "Requirement already satisfied: certifi>=2022.12.07 in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (2022.12.7)\n", "Requirement already satisfied: python-docx in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (0.8.11)\n", "Requirement already satisfied: python-pptx in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (0.6.21)\n", "Requirement already satisfied: python-magic in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (0.4.27)\n", "Requirement already satisfied: msg-parser in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (1.2.0)\n", "Requirement already satisfied: pypandoc in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (1.11)\n", "Requirement already satisfied: unstructured-inference~=0.2.4 in /usr/local/lib/python3.9/dist-packages (from unstructured[local-inference]) (0.2.11)\n", "Requirement already satisfied: uvicorn in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (0.21.1)\n", "Requirement already satisfied: opencv-python==4.6.0.66 in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (4.6.0.66)\n", "Requirement already satisfied: python-multipart in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (0.0.6)\n", "Requirement already satisfied: transformers in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (4.27.4)\n", "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (0.13.3)\n", "Requirement already satisfied: fastapi in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (0.95.0)\n", "Requirement already satisfied: layoutparser[layoutmodels,tesseract] in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (0.3.4)\n", "Requirement already satisfied: onnxruntime in /usr/local/lib/python3.9/dist-packages (from unstructured-inference~=0.2.4->unstructured[local-inference]) (1.14.1)\n", "Requirement already satisfied: numpy>=1.14.5 in /usr/local/lib/python3.9/dist-packages (from opencv-python==4.6.0.66->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.22.4)\n", "Requirement already satisfied: deprecated~=1.2.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (1.2.13)\n", "Requirement already satisfied: wrapt<1.15,>=1.13 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (1.14.1)\n", "Requirement already satisfied: backoff in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (2.2.1)\n", "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (4.65.0)\n", "Requirement already satisfied: pydantic>=1.7.1 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (1.10.7)\n", "Requirement already satisfied: rich<=13.0.1 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (13.0.1)\n", "Requirement already satisfied: httpx<0.24,>=0.15 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (0.23.3)\n", "Requirement already satisfied: monotonic in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (1.6)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from argilla->unstructured[local-inference]) (23.0)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->unstructured[local-inference]) (2022.7.1)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->unstructured[local-inference]) (2.8.2)\n", "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.9/dist-packages (from markdown->unstructured[local-inference]) (6.1.0)\n", "Requirement already satisfied: olefile>=0.46 in /usr/local/lib/python3.9/dist-packages (from msg-parser->unstructured[local-inference]) (0.46)\n", "Requirement already satisfied: click in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured[local-inference]) (8.1.3)\n", "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured[local-inference]) (2022.10.31)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.9/dist-packages (from nltk->unstructured[local-inference]) (1.1.1)\n", "Requirement already satisfied: et-xmlfile in /usr/local/lib/python3.9/dist-packages (from openpyxl->unstructured[local-inference]) (1.1.0)\n", "Requirement already satisfied: XlsxWriter>=0.5.7 in /usr/local/lib/python3.9/dist-packages (from python-pptx->unstructured[local-inference]) (3.0.9)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured[local-inference]) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured[local-inference]) (3.4)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->unstructured[local-inference]) (1.26.15)\n", "Requirement already satisfied: sniffio in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured[local-inference]) (1.3.0)\n", "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured[local-inference]) (0.16.3)\n", "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in /usr/local/lib/python3.9/dist-packages (from httpx<0.24,>=0.15->argilla->unstructured[local-inference]) (1.5.0)\n", "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/dist-packages (from importlib-metadata>=4.4->markdown->unstructured[local-inference]) (3.15.0)\n", "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic>=1.7.1->argilla->unstructured[local-inference]) (4.5.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->unstructured[local-inference]) (1.16.0)\n", "Requirement already satisfied: commonmark<0.10.0,>=0.9.0 in /usr/local/lib/python3.9/dist-packages (from rich<=13.0.1->argilla->unstructured[local-inference]) (0.9.1)\n", "Requirement already satisfied: pygments<3.0.0,>=2.6.0 in /usr/local/lib/python3.9/dist-packages (from rich<=13.0.1->argilla->unstructured[local-inference]) (2.14.0)\n", "Requirement already satisfied: starlette<0.27.0,>=0.26.1 in /usr/local/lib/python3.9/dist-packages (from fastapi->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.26.1)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.10.7)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub->unstructured-inference~=0.2.4->unstructured[local-inference]) (6.0)\n", "Requirement already satisfied: pdfplumber in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.8.0)\n", "Requirement already satisfied: pdf2image in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.16.3)\n", "Requirement already satisfied: iopath in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.1.10)\n", "Requirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.10.1)\n", "Requirement already satisfied: torch in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.0.0+cu118)\n", "Requirement already satisfied: effdet in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.3.0)\n", "Requirement already satisfied: torchvision in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.15.1+cu118)\n", "Requirement already satisfied: pytesseract in /usr/local/lib/python3.9/dist-packages (from layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.3.10)\n", "Requirement already satisfied: coloredlogs in /usr/local/lib/python3.9/dist-packages (from onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (15.0.1)\n", "Requirement already satisfied: flatbuffers in /usr/local/lib/python3.9/dist-packages (from onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (23.3.3)\n", "Requirement already satisfied: protobuf in /usr/local/lib/python3.9/dist-packages (from onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.20.3)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.9/dist-packages (from onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.11.1)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.13.3)\n", "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.9/dist-packages (from uvicorn->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.14.0)\n", "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.9/dist-packages (from httpcore<0.17.0,>=0.15.0->httpx<0.24,>=0.15->argilla->unstructured[local-inference]) (3.6.2)\n", "Requirement already satisfied: humanfriendly>=9.1 in /usr/local/lib/python3.9/dist-packages (from coloredlogs->onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (10.0)\n", "Requirement already satisfied: timm>=0.4.12 in /usr/local/lib/python3.9/dist-packages (from effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.6.13)\n", "Requirement already satisfied: omegaconf>=2.0 in /usr/local/lib/python3.9/dist-packages (from effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.3.0)\n", "Requirement already satisfied: pycocotools>=2.0.2 in /usr/local/lib/python3.9/dist-packages (from effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.0.6)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.9/dist-packages (from torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.1.2)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.9/dist-packages (from torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.0)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.9/dist-packages (from torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.25.2)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (16.0.0)\n", "Requirement already satisfied: portalocker in /usr/local/lib/python3.9/dist-packages (from iopath->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.7.0)\n", "Requirement already satisfied: pdfminer.six==20221105 in /usr/local/lib/python3.9/dist-packages (from pdfplumber->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (20221105)\n", "Requirement already satisfied: Wand>=0.6.10 in /usr/local/lib/python3.9/dist-packages (from pdfplumber->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.6.11)\n", "Requirement already satisfied: cryptography>=36.0.0 in /usr/local/lib/python3.9/dist-packages (from pdfminer.six==20221105->pdfplumber->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (40.0.1)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.9/dist-packages (from sympy->onnxruntime->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.3.0)\n", "Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.9/dist-packages (from omegaconf>=2.0->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (4.9.3)\n", "Requirement already satisfied: matplotlib>=2.1.0 in /usr/local/lib/python3.9/dist-packages (from pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.7.1)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.9/dist-packages (from jinja2->torch->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.1.2)\n", "Requirement already satisfied: cffi>=1.12 in /usr/local/lib/python3.9/dist-packages (from cryptography>=36.0.0->pdfminer.six==20221105->pdfplumber->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.15.1)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.0.7)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (3.0.9)\n", "Requirement already satisfied: importlib-resources>=3.2.0 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (5.12.0)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (4.39.3)\n", "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (1.4.4)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.9/dist-packages (from matplotlib>=2.1.0->pycocotools>=2.0.2->effdet->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (0.11.0)\n", "Requirement already satisfied: pycparser in /usr/local/lib/python3.9/dist-packages (from cffi>=1.12->cryptography>=36.0.0->pdfminer.six==20221105->pdfplumber->layoutparser[layoutmodels,tesseract]->unstructured-inference~=0.2.4->unstructured[local-inference]) (2.21)\n" ] } ] }, { "cell_type": "code", "source": [ "from langchain.document_loaders import UnstructuredPDFLoader, OnlinePDFLoader\n", "from langchain.text_splitter import RecursiveCharacterTextSplitter" ], "metadata": { "id": "oTNaVYzud_AJ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "loader = UnstructuredPDFLoader(\"Your_PDF\")" ], "metadata": { "id": "JKj_kT9zeCzc" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "data = loader.load()\n", "data" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "N7l1clI3eMly", "outputId": "09a5518a-7edf-49a2-9517-823db3bc57b7" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "WARNING:unstructured:detectron2 is not installed. Cannot use the hi_res partitioning strategy. Falling back to partitioning with the fast strategy.\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "[Document(page_content=\"Project Brief\\n\\nThis project is about developing a chatbot or Q&A bot that utilizes NLP and ML to provide logical and\\n\\nprecise answers to user inquiries about website content, including PDFs. The chatbot will be integrated\\n\\nwith the website via Flask or Django and connected to a SQL database for data retrieval. The aim is to\\n\\nenhance user engagement and satisfaction with precise and accurate responses.\\n\\n12 March, 2023\\n\\nOverall, the goal of this project is to make a chatbot that I can use on my website to improve user\\n\\nengagement and satisfaction by answering their questions in a way that is accurate and makes sense. By\\n\\nintegrating the chatbot with my website and SQL database, I can provide users with more comprehensive\\n\\nresponses and help them find the information they need more easily.\\n\\nTechnical Requirements: (suggestive, and open to any alternatives)\\n\\n1. Choose a chatbot platform, such as Rasa, Botpress, or Microsoft Bot Framework, that can be\\n\\nintegrated with Hugging Face's models and my website.\\n\\n2. Collect and preprocess data from my website, including text from web pages, blog posts, product\\n\\ncatalogs, customer service information, and FAQs.\\n\\n3. Fine-tune the Hugging Face model on my specific dataset to improve its accuracy and\\n\\nperformance.\\n\\nIntegrate the chatbot with my website using a web framework such as Flask or Django.\\n\\n4.\\n\\n5. Connect the chatbot to my SQL database to retrieve data and provide relevant responses to user\\n\\n6.\\n\\nqueries.\\n\\nImplement personalized features, analytics, and reporting to track user interactions and identify\\n\\nareas for improvement.\\n\\n7. Test the chatbot thoroughly to ensure that it is working correctly and providing accurate\\n\\nresponses.\\n\\n8. Deploy the chatbot to a server or cloud instance that is scalable and secure.\\n\\nData Sources: The chatbot should be trained on data from my website, including text from web pages,\\n\\nblog posts, PDFs and other content. The chatbot should also be able to access and search a database of\\n\\ncontent, like a catalog of products or information about customer service, to give more complete answers\\n\\nto user questions. Here is a sample site: https://catimes.mybenefitsapp.com/\\n\\nFeatures: The chatbot should have the following features:\\n\\nIntegration with my website's search functionality.\\n\\n1. Ability to understand and respond to natural language queries from users.\\n\\n2.\\n\\n3. Ability to provide relevant information about products, services, or other content on my website.\\n\\n4. Personalization features, such as remembering user preferences or past queries.\\n\\n5. Analytics and reporting features to track user interactions and identify areas for improvement.\\n\\n6. A feature that shows the source of the answer to build user trust.\\n\\nMojo Solo | 275 4th Street East, Suite 323, Saint Paul, MN 55101 | 651.789.6656 |\\n\\ninfo@mojosolo.com\", metadata={'source': 'MojoSolo-NLP-ML-Project.pdf'})]" ] }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "print (f'You have {len(data)} document(s) in your data')\n", "print (f'There are {len(data[0].page_content)} characters in your document')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "RNyCn_r_fDXn", "outputId": "34b84a2b-36e7-418d-82df-bb49db93fb3c" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "You have 1 document(s) in your data\n", "There are 2833 characters in your document\n" ] } ] }, { "cell_type": "code", "source": [ "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n", "texts = text_splitter.split_documents(data)" ], "metadata": { "id": "7vwRLdcjfK9R" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "print (f'Now you have {len(texts)} documents')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "uBYV1TB-fPVf", "outputId": "03219195-6b5d-44c2-dac8-4a2e8b7cd073" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Now you have 3 documents\n" ] } ] }, { "cell_type": "code", "source": [ "!pip3 install pinecone-client" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "lbBLJMx_fbIw", "outputId": "de9530c0-ee3d-4ec8-f910-57f76b360d24" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting pinecone-client\n", " Downloading pinecone_client-2.2.1-py3-none-any.whl (177 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m177.2/177.2 KB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (2.27.1)\n", "Requirement already satisfied: typing-extensions>=3.7.4 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (4.5.0)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (1.22.4)\n", "Collecting loguru>=0.5.0\n", " Downloading loguru-0.6.0-py3-none-any.whl (58 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 KB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting dnspython>=2.0.0\n", " Downloading dnspython-2.3.0-py3-none-any.whl (283 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m283.7/283.7 KB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: urllib3>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (1.26.15)\n", "Requirement already satisfied: pyyaml>=5.4 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (6.0)\n", "Requirement already satisfied: tqdm>=4.64.1 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (4.65.0)\n", "Requirement already satisfied: python-dateutil>=2.5.3 in /usr/local/lib/python3.9/dist-packages (from pinecone-client) (2.8.2)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.5.3->pinecone-client) (1.16.0)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->pinecone-client) (3.4)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->pinecone-client) (2.0.12)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->pinecone-client) (2022.12.7)\n", "Installing collected packages: loguru, dnspython, pinecone-client\n", "Successfully installed dnspython-2.3.0 loguru-0.6.0 pinecone-client-2.2.1\n" ] } ] }, { "cell_type": "code", "source": [ "from langchain.vectorstores import Chroma, Pinecone\n", "from langchain.embeddings.openai import OpenAIEmbeddings\n", "import pinecone" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "55yTna8ffR8K", "outputId": "65b41aab-503e-4ce9-8281-ba9302ffaa8a" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.9/dist-packages/pinecone/index.py:4: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n", " from tqdm.autonotebook import tqdm\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "OPENAI_API_KEY = 'Your_OpenAI_Key'\n", "PINECONE_API_KEY = 'Your_Pinecone_Key'\n", "PINECONE_API_ENV = 'PineconeEnvironemt'" ], "metadata": { "id": "Tupo_xlgfocy" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "!pip install openai" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yOM0YXSkgE9p", "outputId": "d9ab7d69-f6d5-4ea5-d411-3b58377bf26d" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting openai\n", " Downloading openai-0.27.4-py3-none-any.whl (70 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m70.3/70.3 KB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: requests>=2.20 in /usr/local/lib/python3.9/dist-packages (from openai) (2.27.1)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from openai) (4.65.0)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.9/dist-packages (from openai) (3.8.4)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (3.4)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2.0.12)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.20->openai) (2022.12.7)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (4.0.2)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.8.2)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.3.3)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (22.2.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (1.3.1)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp->openai) (6.0.4)\n", "Installing collected packages: openai\n", "Successfully installed openai-0.27.4\n" ] } ] }, { "cell_type": "code", "source": [ "embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)" ], "metadata": { "id": "KfUAcVgzf-1C" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# initialize pinecone\n", "pinecone.init(\n", " api_key=PINECONE_API_KEY, # find at app.pinecone.io\n", " environment=PINECONE_API_ENV # next to api key in console\n", ")\n", "index_name = \"mojosolo\"" ], "metadata": { "id": "OIPcu5gQgKKp" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "docsearch = Pinecone.from_texts([t.page_content for t in texts], embeddings, index_name=index_name)" ], "metadata": { "id": "WvrXQngEgPZ8" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "query = \"What are the technical requirements?\"\n", "docs = docsearch.similarity_search(query, include_metadata=True)" ], "metadata": { "id": "uDeZWYu2fUuC" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "from langchain.llms import OpenAI\n", "from langchain.chains.question_answering import load_qa_chain" ], "metadata": { "id": "HBXGyUUFgvEh" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "llm = OpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)\n", "chain = load_qa_chain(llm, chain_type=\"stuff\")" ], "metadata": { "id": "xqjq2_wQgxQl" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "query = \"What are the technical requirements?\"\n", "docs = docsearch.similarity_search(query, include_metadata=True)" ], "metadata": { "id": "NU2J-fclgzwJ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "chain.run(input_documents=docs, question=query)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 147 }, "id": "VS_QtL8eg12r", "outputId": "bc1eccbf-69cc-46c7-a7ca-ed2961382645" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "\" The technical requirements are to choose a chatbot platform, such as Rasa, Botpress, or Microsoft Bot Framework, that can be integrated with Hugging Face's models and my website; collect and preprocess data from my website, including text from web pages, blog posts, product catalogs, customer service information, and FAQs; fine-tune the Hugging Face model on my specific dataset to improve its accuracy and performance; integrate the chatbot with my website using a web framework such as Flask or Django; connect the chatbot to my SQL database to retrieve data and provide relevant responses to user queries; implement personalized features, analytics, and reporting to track user interactions and identify areas for improvement; test the chatbot thoroughly to ensure that it is working correctly and providing accurate responses; and deploy the chatbot to a server or cloud instance that is scalable and secure.\"" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" } }, "metadata": {}, "execution_count": 25 } ] } ] }