Name | goldretriever JSON |
Version |
0.1.5
JSON |
| download |
home_page | |
Summary | Create and host retrieval plugins for ChatGPT in one click |
upload_time | 2023-07-21 13:33:52 |
maintainer | |
docs_url | None |
author | Jina AI |
requires_python | >=3.8,<4.0 |
license | |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# 🐕 Gold Retriever
>Powered by [Jina](https://github.com/jina-ai/jina) and [DocArray](https://github.com/docarray/docarray)
Easily empower ChatGPT to store and analyze your data using `goldretriever`, a powerful command-line tool for creating and hosting retrieval plugins in just a few simple steps.
![Blog images](https://github.com/jina-ai/GoldRetriever/assets/45267439/e722a8a8-3308-45a4-a7f6-34c71f5a2215)
### 🎬 Showcase: Real-world Plugin Creations
- Personal Study Assistant - [Blog](https://jina.ai/news/gold-retriever-let-chatgpt-talk-to-your-data/) | [Video](https://www.youtube.com/watch?v=gQz-vuo8w5I)
## ⚡ Quick Start
### 📦 Installation
1. Ensure you have Python 3.8 or later.
2. Install the tool via pip:
```bash
pip install goldretriever
```
### 🚀 Deployment
1. Run the following command to deploy the plugin:
```bash
goldretriever deploy --key <your openai key>
```
2. Store the "Gateway (Http)" URL and the Bearer token provided in the output.
```bash
╭──────────────────────── 🎉 Flow is available! ────────────────────────╮
│ │
│ ID retrieval-plugin-<plugin id> │
│ Gateway (Http) https://retrieval-plugin-<plugin id>.wolf.jina.ai │
│ Dashboard https://dashboard.wolf.jina.ai/flow/<plugin id> │
│ │
╰───────────────────────────────────────────────────────────────────────╯
Bearer token: <your bearer token>
```
### 📚 Data Indexing
1. Gather relevant text data files (PDF, TXT, DOCX, PPTX, or MD) in a directory.
2. Index the data:
```bash
goldretriever index --data my_files
```
Or, use `docarray (v0.21.0)` for text data:
```python
from docarray import Document, DocumentArray
texts = ['Text 1', 'Text 2', 'Text 3']
docs = DocumentArray([Document(text=text) for text in texts])
docs.save_binary('docs.bin')
```
And then:
```bash
goldretriever index --data docs.bin
```
### 🔗 Integration
1. Go to OpenAI Plugins.
2. Select "Develop your own plugin".
3. Enter the "Gateway (Http)" URL and Bearer token from the deployment step.
## 🎛️ Advanced Usage
### 🛠️ Configuration
To tailor the plugin to your needs, change the name and description during deployment:
```bash
goldretriever deploy --key <your openai key> --name "Custom Name" --description "Custom description"
```
If not specified, default values will be used.
| Argument | Description | Default Value |
|:------------|:----------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| name | Human-readable name, such as the full company name | Gold Retriever |
| description | Description better tailored to the model, such as token context length considerations or keyword usage for improved plugin prompting | Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information |
### 📋 Listing Plugins
List your plugins and their status:
```bash
goldretriever list
```
Output:
```bash
Plugin ID: ece735568f | Status: Serving
```
### 🗑️ Deleting Plugins
Delete a plugin:
```bash
goldretriever delete <plugin id>
```
### 🔍 Indexing Specific Plugins
Index data for a specific plugin:
```bash
goldretriever index --data my_files --id <plugin_id>
```
If the plugin ID is not specified, the last created plugin will be indexed.
## 🎓 Acknowledgements
This project is built upon the open-source [chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) repository developed by OpenAI.
Raw data
{
"_id": null,
"home_page": "",
"name": "goldretriever",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<4.0",
"maintainer_email": "",
"keywords": "",
"author": "Jina AI",
"author_email": "hello@jina.ai",
"download_url": "https://files.pythonhosted.org/packages/b0/73/9094896e56d796bf302fb2fe9bb16ef34acbf04ba31c76b4227f327a98ca/goldretriever-0.1.5.tar.gz",
"platform": null,
"description": "# \ud83d\udc15 Gold Retriever\n>Powered by [Jina](https://github.com/jina-ai/jina) and [DocArray](https://github.com/docarray/docarray)\n\nEasily empower ChatGPT to store and analyze your data using `goldretriever`, a powerful command-line tool for creating and hosting retrieval plugins in just a few simple steps.\n\n![Blog images](https://github.com/jina-ai/GoldRetriever/assets/45267439/e722a8a8-3308-45a4-a7f6-34c71f5a2215)\n\n### \ud83c\udfac Showcase: Real-world Plugin Creations\n\n- Personal Study Assistant - [Blog](https://jina.ai/news/gold-retriever-let-chatgpt-talk-to-your-data/) | [Video](https://www.youtube.com/watch?v=gQz-vuo8w5I)\n\n## \u26a1 Quick Start\n\n### \ud83d\udce6 Installation\n\n1. Ensure you have Python 3.8 or later.\n2. Install the tool via pip:\n ```bash\n pip install goldretriever\n ```\n\n### \ud83d\ude80 Deployment\n1. Run the following command to deploy the plugin:\n```bash\ngoldretriever deploy --key <your openai key>\n```\n2. Store the \"Gateway (Http)\" URL and the Bearer token provided in the output.\n```bash\n\u256d\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \ud83c\udf89 Flow is available! \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256e\n\u2502 \u2502\n\u2502 ID retrieval-plugin-<plugin id> \u2502\n\u2502 Gateway (Http) https://retrieval-plugin-<plugin id>.wolf.jina.ai \u2502\n\u2502 Dashboard https://dashboard.wolf.jina.ai/flow/<plugin id> \u2502\n\u2502 \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nBearer token: <your bearer token>\n```\n\n### \ud83d\udcda Data Indexing\n1. Gather relevant text data files (PDF, TXT, DOCX, PPTX, or MD) in a directory.\n2. Index the data:\n```bash\ngoldretriever index --data my_files\n```\n Or, use `docarray (v0.21.0)` for text data:\n```python\nfrom docarray import Document, DocumentArray\n\ntexts = ['Text 1', 'Text 2', 'Text 3']\ndocs = DocumentArray([Document(text=text) for text in texts])\ndocs.save_binary('docs.bin')\n```\nAnd then:\n```bash\ngoldretriever index --data docs.bin\n```\n\n### \ud83d\udd17 Integration\n1. Go to OpenAI Plugins.\n2. Select \"Develop your own plugin\".\n3. Enter the \"Gateway (Http)\" URL and Bearer token from the deployment step.\n\n\n## \ud83c\udf9b\ufe0f Advanced Usage\n\n\n### \ud83d\udee0\ufe0f Configuration\nTo tailor the plugin to your needs, change the name and description during deployment:\n```bash\ngoldretriever deploy --key <your openai key> --name \"Custom Name\" --description \"Custom description\"\n```\nIf not specified, default values will be used.\n\n| Argument | Description | Default Value |\n|:------------|:----------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| name | Human-readable name, such as the full company name\t | Gold Retriever |\n| description | Description better tailored to the model, such as token context length considerations or keyword usage for improved plugin prompting | Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information |\n\n\n\n### \ud83d\udccb Listing Plugins\nList your plugins and their status:\n```bash\ngoldretriever list\n```\n\nOutput:\n```bash\nPlugin ID: ece735568f | Status: Serving\n```\n\n### \ud83d\uddd1\ufe0f Deleting Plugins\nDelete a plugin:\n```bash\ngoldretriever delete <plugin id>\n```\n\n### \ud83d\udd0d Indexing Specific Plugins\nIndex data for a specific plugin:\n```bash\ngoldretriever index --data my_files --id <plugin_id>\n```\nIf the plugin ID is not specified, the last created plugin will be indexed.\n\n## \ud83c\udf93 Acknowledgements\nThis project is built upon the open-source [chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) repository developed by OpenAI.\n\n",
"bugtrack_url": null,
"license": "",
"summary": "Create and host retrieval plugins for ChatGPT in one click",
"version": "0.1.5",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e13705a9a534a56fbde47b294d6d7fac7624ebc89ecd99bc6275c92626c0d679",
"md5": "6956f31545cf0aac199165cdbe33f97a",
"sha256": "e8fcff11444c0f9deea60200acc6714511afff9155ea551bdc9f73acd5ce0d96"
},
"downloads": -1,
"filename": "goldretriever-0.1.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6956f31545cf0aac199165cdbe33f97a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<4.0",
"size": 90574,
"upload_time": "2023-07-21T13:33:50",
"upload_time_iso_8601": "2023-07-21T13:33:50.357763Z",
"url": "https://files.pythonhosted.org/packages/e1/37/05a9a534a56fbde47b294d6d7fac7624ebc89ecd99bc6275c92626c0d679/goldretriever-0.1.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b0739094896e56d796bf302fb2fe9bb16ef34acbf04ba31c76b4227f327a98ca",
"md5": "b6a3e795763d29e025fe952117d22e16",
"sha256": "8fd7c3460cff0d778f62929c3fd20a44ccd9691db539451f9f5abb0691df76a2"
},
"downloads": -1,
"filename": "goldretriever-0.1.5.tar.gz",
"has_sig": false,
"md5_digest": "b6a3e795763d29e025fe952117d22e16",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<4.0",
"size": 80440,
"upload_time": "2023-07-21T13:33:52",
"upload_time_iso_8601": "2023-07-21T13:33:52.517936Z",
"url": "https://files.pythonhosted.org/packages/b0/73/9094896e56d796bf302fb2fe9bb16ef34acbf04ba31c76b4227f327a98ca/goldretriever-0.1.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-21 13:33:52",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "goldretriever"
}