klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Sidharth Mohanty
2023-10-18 21:34:06 +05:30
committed by GitHub
parent 65a20aa457
commit b2286f3e34
12 changed files with 2299 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

185
notebooks/anthropic.ipynb Normal file
View File

@@ -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
}

171
notebooks/chromadb.ipynb Normal file
View File

@@ -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": []
}
]
}

205
notebooks/cohere.ipynb Normal file
View File

@@ -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
}

180
notebooks/elasticsearch.ipynb Normal file
View File

@@ -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": []
}
]
}

205
notebooks/gpt4all.ipynb Normal file
View File

@@ -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
}

228
notebooks/hugging_face_hub.ipynb Normal file
View File

@@ -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
}

189
notebooks/jina.ipynb Normal file
View File

@@ -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
}

196
notebooks/llama2.ipynb Normal file
View File

@@ -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
}

181
notebooks/openai.ipynb Normal file
View File

@@ -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
}

184
notebooks/opensearch.ipynb Normal file
View File

@@ -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": []
}
]
}

181
notebooks/pinecone.ipynb Normal file
View File

@@ -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
}

194
notebooks/vertex_ai.ipynb Normal file
View File

@@ -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
}