Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Google Colab Notebooks for LLMs, Embedders and VectorDBs (#821)

Sidharth Mohantyb2286f3e3466
diff --git a/notebooks/anthropic.ipynb b/notebooks/anthropic.ipynb
new file mode 100644
index 000000000..47ff6cb71
--- /dev/null
+++ b/notebooks/anthropic.ipynb
@@ -0,0 +1,185 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using Anthropic with Embedchain\n",
+ "\n"
+ ]
+ },
+ {
+ "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": "efdce0dc-fb30-4e01-f5a8-ef1a7f4e8c09"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set Anthropic related environment variables\n",
+ "\n",
+ "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `ANTHROPIC_API_KEY` on your [Anthropic dashboard](https://console.anthropic.com/account/keys)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+ "os.environ[\"ANTHROPIC_API_KEY\"] = \"xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: anthropic\n",
+ " config:\n",
+ " model: 'claude-instant-1'\n",
+ " temperature: 0.5\n",
+ " top_p: 1\n",
+ " stream: false\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('anthropic.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": null,
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"anthropic.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 52
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "dc17baec-39b5-4dc8-bd42-f2aad92697eb"
+ },
+ "outputs": [],
+ "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/",
+ "height": 391
+ },
+ "id": "cvIK7dWRjN_f",
+ "outputId": "3d1cb7ce-969e-4dad-d48c-b818b7447cc0"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/chromadb.ipynb b/notebooks/chromadb.ipynb
new file mode 100644
index 000000000..16e189b7f
--- /dev/null
+++ b/notebooks/chromadb.ipynb
@@ -0,0 +1,171 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Cookbook for using ChromaDB with Embedchain"
+ ],
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-1: Install embedchain package"
+ ],
+ "metadata": {
+ "id": "gyJ6ui2vhtMY"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install embedchain"
+ ],
+ "metadata": {
+ "id": "-NbXjAdlh0vJ"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-2: Set OpenAI environment variables\n",
+ "\n",
+ "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys)."
+ ],
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\""
+ ],
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-3: Define your Vector Database config"
+ ],
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "config = \"\"\"\n",
+ "vectordb:\n",
+ " provider: chroma\n",
+ " config:\n",
+ " collection_name: 'my-collection'\n",
+ " # CHANGE THE BELOW TWO LINES!\n",
+ " # pass remote database variables - host and port\n",
+ " host: your-chromadb-url.com\n",
+ " port: 5200\n",
+ " allow_reset: true\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('chromadb.yaml', 'w') as file:\n",
+ " file.write(config)"
+ ],
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-4 Create embedchain app based on the config"
+ ],
+ "metadata": {
+ "id": "PGt6uPLIi1CS"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app = App.from_config(yaml_path=\"chromadb.yaml\")"
+ ],
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ],
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app.add(\"https://www.forbes.com/profile/elon-musk\")"
+ ],
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-6: All set. Now start asking questions related to your data"
+ ],
+ "metadata": {
+ "id": "_7W6fDeAjMAP"
+ }
+ },
+ {
+ "cell_type": "code",
+ "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)"
+ ],
+ "metadata": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
diff --git a/notebooks/cohere.ipynb b/notebooks/cohere.ipynb
new file mode 100644
index 000000000..3831b80f6
--- /dev/null
+++ b/notebooks/cohere.ipynb
@@ -0,0 +1,205 @@
+{
+ "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"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set Cohere related environment variables and install the dependencies\n",
+ "\n",
+ "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `COHERE_API_KEY` key on your [Cohere dashboard](https://dashboard.cohere.com/api-keys)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000
+ },
+ "id": "S5jTywPZNtrj",
+ "outputId": "4a23c813-c9e5-4b6c-e3d9-b41e4fdbc54d"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain[cohere]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+ "os.environ[\"COHERE_API_KEY\"] = \"xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: cohere\n",
+ " config:\n",
+ " model: gptd-instruct-tft\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 1\n",
+ " stream: false\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('cohere.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": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 321
+ },
+ "id": "Amzxk3m-i3tD",
+ "outputId": "afe8afde-5cb8-46bc-c541-3ad26cc3fa6e"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"cohere.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 176
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "2f2718a4-3b7e-4844-fd46-3e0857653ca0"
+ },
+ "outputs": [],
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/elasticsearch.ipynb b/notebooks/elasticsearch.ipynb
new file mode 100644
index 000000000..4bb69ad1d
--- /dev/null
+++ b/notebooks/elasticsearch.ipynb
@@ -0,0 +1,180 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Cookbook for using ElasticSearchDB with Embedchain"
+ ],
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-1: Install embedchain package"
+ ],
+ "metadata": {
+ "id": "gyJ6ui2vhtMY"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install embedchain"
+ ],
+ "metadata": {
+ "id": "-NbXjAdlh0vJ"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-2: Set OpenAI environment variables and install the dependencies.\n",
+ "\n",
+ "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys). Now lets install the dependencies needed for Elasticsearch."
+ ],
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install --upgrade 'embedchain[elasticsearch]'"
+ ],
+ "metadata": {
+ "id": "-MUFRfxV7Jk7"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\""
+ ],
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-3: Define your Vector Database config"
+ ],
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "config = \"\"\"\n",
+ "vectordb:\n",
+ " provider: elasticsearch\n",
+ " config:\n",
+ " collection_name: 'es-index'\n",
+ " es_url: your-elasticsearch-url.com\n",
+ " allow_reset: true\n",
+ " api_key: xxx\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('elasticsearch.yaml', 'w') as file:\n",
+ " file.write(config)"
+ ],
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-4 Create embedchain app based on the config"
+ ],
+ "metadata": {
+ "id": "PGt6uPLIi1CS"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app = App.from_config(yaml_path=\"elasticsearch.yaml\")"
+ ],
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ],
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app.add(\"https://www.forbes.com/profile/elon-musk\")"
+ ],
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-6: All set. Now start asking questions related to your data"
+ ],
+ "metadata": {
+ "id": "_7W6fDeAjMAP"
+ }
+ },
+ {
+ "cell_type": "code",
+ "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)"
+ ],
+ "metadata": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
diff --git a/notebooks/gpt4all.ipynb b/notebooks/gpt4all.ipynb
new file mode 100644
index 000000000..951bb76a2
--- /dev/null
+++ b/notebooks/gpt4all.ipynb
@@ -0,0 +1,205 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using GPT4All 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": "077fa470-b51f-4c29-8c22-9c5f0a9cef47"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set GPT4ALL related environment variables and install dependencies\n",
+ "\n",
+ "GPT4All is free for all and doesn't require any API Key to use it. Just import the dependencies."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "dGOE4u3dC6at",
+ "outputId": "c1c0087b-3f14-49fa-fb86-a4a3391ba14c"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install --upgrade embedchain[opensource]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "from embedchain import App"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: gpt4all\n",
+ " config:\n",
+ " model: 'orca-mini-3b.ggmlv3.q4_0.bin'\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 1\n",
+ " stream: false\n",
+ "\n",
+ "embedder:\n",
+ " provider: gpt4all\n",
+ " config:\n",
+ " model: 'all-MiniLM-L6-v2'\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('gpt4all.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": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "Amzxk3m-i3tD",
+ "outputId": "775db99b-e217-47db-f87f-788495d86f26"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"gpt4all.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 52
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "c6514f17-3cb2-4fbc-c80d-79b3a311ff30"
+ },
+ "outputs": [],
+ "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/",
+ "height": 480
+ },
+ "id": "cvIK7dWRjN_f",
+ "outputId": "c74f356a-d2fb-426d-b36c-d84911397338"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/hugging_face_hub.ipynb b/notebooks/hugging_face_hub.ipynb
new file mode 100644
index 000000000..868d4cdce
--- /dev/null
+++ b/notebooks/hugging_face_hub.ipynb
@@ -0,0 +1,228 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using Hugging Face Hub 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/",
+ "height": 1000
+ },
+ "id": "-NbXjAdlh0vJ",
+ "outputId": "35ddc904-8067-44cf-dcc9-3c8b4cd29989"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set Hugging Face Hub related environment variables and install dependencies\n",
+ "\n",
+ "You can find your `HUGGINGFACE_ACCESS_TOKEN` key on your [Hugging Face Hub dashboard](https://huggingface.co/settings/tokens) and install the dependencies"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "VfDNZJCqNfqo",
+ "outputId": "34894d35-7142-42ee-8564-2e9f718afcbb"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain[huggingface-hub]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "SCNT8khqcR3G",
+ "outputId": "b789ee77-ef50-4330-8ac6-5da645dc36d6"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain[opensource]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"HUGGINGFACE_ACCESS_TOKEN\"] = \"hf_xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: huggingface\n",
+ " config:\n",
+ " model: 'google/flan-t5-xxl'\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 0.8\n",
+ " stream: false\n",
+ "\n",
+ "embedder:\n",
+ " provider: huggingface\n",
+ " config:\n",
+ " model: 'sentence-transformers/all-mpnet-base-v2'\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('huggingface.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": null,
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"huggingface.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 70
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "3c2a803a-3a93-4b0d-a6ae-17ae3c96c3c2"
+ },
+ "outputs": [],
+ "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": "47a89d1c-b322-495c-822a-6c2ecef894d2"
+ },
+ "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": {
+ "id": "HvZVn6gU5xB_"
+ },
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/jina.ipynb b/notebooks/jina.ipynb
new file mode 100644
index 000000000..801d25b77
--- /dev/null
+++ b/notebooks/jina.ipynb
@@ -0,0 +1,189 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using JinaChat 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/",
+ "height": 1000
+ },
+ "id": "-NbXjAdlh0vJ",
+ "outputId": "69cb79a6-c758-4656-ccf7-9f3105c81d16"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set JinaChat related environment variables\n",
+ "\n",
+ "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `JINACHAT_API_KEY` key on your [Chat Jina dashboard](https://chat.jina.ai/api)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+ "os.environ[\"JINACHAT_API_KEY\"] = \"xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: jina\n",
+ " config:\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 1\n",
+ " stream: false\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('jina.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": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 321
+ },
+ "id": "Amzxk3m-i3tD",
+ "outputId": "8d00da74-5f73-49bb-b868-dcf1c375ac85"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"jina.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 52
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "10eeacc7-9263-448e-876d-002af897ebe5"
+ },
+ "outputs": [],
+ "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": "7dc7212f-a0e9-43c8-f119-f595ba79b4b7"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/llama2.ipynb b/notebooks/llama2.ipynb
new file mode 100644
index 000000000..8852d5937
--- /dev/null
+++ b/notebooks/llama2.ipynb
@@ -0,0 +1,196 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using LLAMA2 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": "86a4a9b2-4ed6-431c-da6f-c3eacb390f42"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set LLAMA2 related environment variables and install dependencies\n",
+ "\n",
+ "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `REPLICATE_API_TOKEN` key on your [Replicate dashboard](https://replicate.com/account/api-tokens). Now lets install the dependencies for LLAMA2."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "qoBUbocNtUUD"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain[llama2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+ "os.environ[\"REPLICATE_API_TOKEN\"] = \"xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: llama2\n",
+ " config:\n",
+ " model: 'a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5'\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 0.5\n",
+ " stream: false\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('llama2.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": null,
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"llama2.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 52
+ },
+ "id": "Sn_0rx9QjIY9",
+ "outputId": "ba158e9c-0f16-4c6b-a876-7543120985a2"
+ },
+ "outputs": [],
+ "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/",
+ "height": 599
+ },
+ "id": "cvIK7dWRjN_f",
+ "outputId": "e2d11a25-a2ed-4034-ec6a-e8a5986c89ae"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/openai.ipynb b/notebooks/openai.ipynb
new file mode 100644
index 000000000..acfbfdcc7
--- /dev/null
+++ b/notebooks/openai.ipynb
@@ -0,0 +1,181 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using OpenAI 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/",
+ "height": 1000
+ },
+ "id": "-NbXjAdlh0vJ",
+ "outputId": "6c630676-c7fc-4054-dc94-c613de58a037"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set OpenAI environment variables\n",
+ "\n",
+ "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: openai\n",
+ " config:\n",
+ " model: gpt-35-turbo\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " top_p: 1\n",
+ " stream: false\n",
+ "\n",
+ "embedder:\n",
+ " provider: openai\n",
+ " config:\n",
+ " model: text-embedding-ada-002\n",
+ " deployment_name: ec_embeddings_ada_002\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('openai.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": null,
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"openai.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "outputs": [],
+ "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": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/opensearch.ipynb b/notebooks/opensearch.ipynb
new file mode 100644
index 000000000..16a6b1e68
--- /dev/null
+++ b/notebooks/opensearch.ipynb
@@ -0,0 +1,184 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Cookbook for using OpenSearchDB with Embedchain"
+ ],
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-1: Install embedchain package"
+ ],
+ "metadata": {
+ "id": "gyJ6ui2vhtMY"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install embedchain"
+ ],
+ "metadata": {
+ "id": "-NbXjAdlh0vJ"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-2: Set OpenAI environment variables and install the dependencies.\n",
+ "\n",
+ "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys). Now lets install the dependencies needed for Opensearch."
+ ],
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install --upgrade 'embedchain[opensearch]'"
+ ],
+ "metadata": {
+ "id": "-MUFRfxV7Jk7"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\""
+ ],
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-3: Define your Vector Database config"
+ ],
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "config = \"\"\"\n",
+ "vectordb:\n",
+ " provider: opensearch\n",
+ " config:\n",
+ " opensearch_url: 'your-opensearch-url.com'\n",
+ " http_auth:\n",
+ " - admin\n",
+ " - admin\n",
+ " vector_dimension: 1536\n",
+ " collection_name: 'my-app'\n",
+ " use_ssl: false\n",
+ " verify_certs: false\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('opensearch.yaml', 'w') as file:\n",
+ " file.write(config)"
+ ],
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-4 Create embedchain app based on the config"
+ ],
+ "metadata": {
+ "id": "PGt6uPLIi1CS"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app = App.from_config(yaml_path=\"opensearch.yaml\")"
+ ],
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ],
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "app.add(\"https://www.forbes.com/profile/elon-musk\")"
+ ],
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Step-6: All set. Now start asking questions related to your data"
+ ],
+ "metadata": {
+ "id": "_7W6fDeAjMAP"
+ }
+ },
+ {
+ "cell_type": "code",
+ "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)"
+ ],
+ "metadata": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
diff --git a/notebooks/pinecone.ipynb b/notebooks/pinecone.ipynb
new file mode 100644
index 000000000..5f6b018d9
--- /dev/null
+++ b/notebooks/pinecone.ipynb
@@ -0,0 +1,181 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using PineconeDB with Embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "gyJ6ui2vhtMY"
+ },
+ "source": [
+ "### Step-1: Install embedchain package"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "-NbXjAdlh0vJ"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set environment variables needed for Pinecone and install the dependencies.\n",
+ "\n",
+ "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and [Pinecone dashboard](https://app.pinecone.io/). Now lets install the dependencies needed for Pinecone."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "-MUFRfxV7Jk7"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install --upgrade 'embedchain[pinecone]'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+ "os.environ[\"PINECONE_API_KEY\"] = \"xxx\"\n",
+ "os.environ[\"PINECONE_ENV\"] = \"xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your Vector Database config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "vectordb:\n",
+ " provider: pinecone\n",
+ " config:\n",
+ " metric: cosine\n",
+ " vector_dimension: 768\n",
+ " collection_name: pc-index\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('pinecone.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": null,
+ "metadata": {
+ "id": "Amzxk3m-i3tD"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"pinecone.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "outputs": [],
+ "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": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/notebooks/vertex_ai.ipynb b/notebooks/vertex_ai.ipynb
new file mode 100644
index 000000000..574f65ea1
--- /dev/null
+++ b/notebooks/vertex_ai.ipynb
@@ -0,0 +1,194 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "b02n_zJ_hl3d"
+ },
+ "source": [
+ "## Cookbook for using VertexAI 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": "eb9be5b6-dc81-43d2-d515-df8f0116be11"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "nGnpSYAAh2bQ"
+ },
+ "source": [
+ "### Step-2: Set VertexAI related environment variables and install dependencies.\n",
+ "\n",
+ "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys). Now lets install the dependencies."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "a_shbIFBtnwu"
+ },
+ "outputs": [],
+ "source": [
+ "!pip install embedchain[vertexai]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "0fBdQ9GAiRvK"
+ },
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from embedchain import App\n",
+ "\n",
+ "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Ns6RhPfbiitr"
+ },
+ "source": [
+ "### Step-3: Define your llm and embedding model config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "S9CkxVjriotB"
+ },
+ "outputs": [],
+ "source": [
+ "config = \"\"\"\n",
+ "llm:\n",
+ " provider: vertexai\n",
+ " config:\n",
+ " model: 'chat-bison'\n",
+ " temperature: 0.5\n",
+ " max_tokens: 1000\n",
+ " stream: false\n",
+ "\n",
+ "embedder:\n",
+ " provider: vertexai\n",
+ " config:\n",
+ " model: 'textembedding-gecko'\n",
+ "\"\"\"\n",
+ "\n",
+ "# Write the multi-line string to a YAML file\n",
+ "with open('vertexai.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": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 582
+ },
+ "id": "Amzxk3m-i3tD",
+ "outputId": "5084b6ea-ec20-4281-9f36-e21e93c17475"
+ },
+ "outputs": [],
+ "source": [
+ "app = App.from_config(yaml_path=\"vertexai.yaml\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XNXv4yZwi7ef"
+ },
+ "source": [
+ "### Step-5: Add data sources to your app"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Sn_0rx9QjIY9"
+ },
+ "outputs": [],
+ "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": {
+ "id": "cvIK7dWRjN_f"
+ },
+ "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)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}