{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "b02n_zJ_hl3d" }, "source": [ "## Cookbook for using Cohere with Embedchain" ] }, { "cell_type": "markdown", "metadata": { "id": "gyJ6ui2vhtMY" }, "source": [ "### Step-1: Install embedchain package" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-NbXjAdlh0vJ", "outputId": "fae77912-4e6a-4c78-fcb7-fbbe46f7a9c7" }, "outputs": [], "source": [ "!pip install embedchain[dataloaders,together]" ] }, { "cell_type": "markdown", "metadata": { "id": "nGnpSYAAh2bQ" }, "source": [ "### Step-2: Set Cohere related environment variables\n", "\n", "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `TOGETHER_API_KEY` key on your [Together dashboard](https://api.together.xyz/settings/api-keys)." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "0fBdQ9GAiRvK" }, "outputs": [], "source": [ "import os\n", "from embedchain import Pipeline as App\n", "\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", "os.environ[\"TOGETHER_API_KEY\"] = \"\"" ] }, { "cell_type": "markdown", "metadata": { "id": "Ns6RhPfbiitr" }, "source": [ "### Step-3: Define your llm and embedding model config" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "S9CkxVjriotB" }, "outputs": [], "source": [ "config = \"\"\"\n", "llm:\n", " provider: together\n", " config:\n", " model: mistralai/Mixtral-8x7B-Instruct-v0.1\n", " temperature: 0.5\n", " max_tokens: 1000\n", "\"\"\"\n", "\n", "# Write the multi-line string to a YAML file\n", "with open('together.yaml', 'w') as file:\n", " file.write(config)" ] }, { "cell_type": "markdown", "metadata": { "id": "PGt6uPLIi1CS" }, "source": [ "### Step-4 Create embedchain app based on the config" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 321 }, "id": "Amzxk3m-i3tD", "outputId": "afe8afde-5cb8-46bc-c541-3ad26cc3fa6e" }, "outputs": [], "source": [ "app = App.from_config(config_path=\"together.yaml\")" ] }, { "cell_type": "markdown", "metadata": { "id": "XNXv4yZwi7ef" }, "source": [ "### Step-5: Add data sources to your app" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 176 }, "id": "Sn_0rx9QjIY9", "outputId": "2f2718a4-3b7e-4844-fd46-3e0857653ca0" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Inserting batches in chromadb: 100%|██████████| 1/1 [00:01<00:00, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Successfully saved https://www.forbes.com/profile/elon-musk (DataType.WEB_PAGE). New chunks count: 4\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] }, { "data": { "text/plain": [ "'8cf46026cabf9b05394a2658bd1fe890'" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "app.add(\"https://www.forbes.com/profile/elon-musk\")" ] }, { "cell_type": "markdown", "metadata": { "id": "_7W6fDeAjMAP" }, "source": [ "### Step-6: All set. Now start asking questions related to your data" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "cvIK7dWRjN_f", "outputId": "79e873c8-9594-45da-f5a3-0a893511267f" }, "outputs": [], "source": [ "while(True):\n", " question = input(\"Enter question: \")\n", " if question in ['q', 'exit', 'quit']:\n", " break\n", " answer = app.query(question)\n", " print(answer)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "colab": { "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": "3.11.4" } }, "nbformat": 4, "nbformat_minor": 0 }