Skip to main content

🐕 Gold Retriever

Powered by Jina and 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

🎬 Showcase: Real-world Plugin Creations

⚡ Quick Start

📦 Installation

  1. Ensure you have Python 3.8 or later.
  2. Install the tool via pip:
pip install goldretriever

🚀 Deployment

  1. Run the following command to deploy the plugin:
goldretriever deploy --key <your openai key>
  1. Store the "Gateway (Http)" URL and the Bearer token provided in the output.
╭──────────────────────── 🎉 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:
goldretriever index --data my_files

Or, use docarray (v0.21.0) for text data:

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:

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:

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:

goldretriever list

Output:

Plugin ID: ece735568f | Status: Serving

🗑️ Deleting Plugins

Delete a plugin:

goldretriever delete <plugin id>

🔍 Indexing Specific Plugins

Index data for a specific plugin:

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 repository developed by OpenAI.

Metadata

Release files for goldretriever 0.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for goldretriever 0.1.5
File Size Uploaded
goldretriever-0.1.5.tar.gz 80.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for goldretriever 0.1.5
File Interpreter ABI Platform
goldretriever-0.1.5-py3-none-any.whl Python 3 none any Details

Total release size: 171.0 kB

Release files / goldretriever-0.1.5.tar.gz

Download URL goldretriever-0.1.5.tar.gz
Size 80.4 kB
Tags Source
SHA-256 checksum
How to use checksums
8fd7c3460cff0d778f62929c3fd20a44ccd9691db539451f9f5abb0691df76a2
BLAKE2b-256 checksum
How to use checksums
b0739094896e56d796bf302fb2fe9bb16ef34acbf04ba31c76b4227f327a98ca
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.17

Release files / goldretriever-0.1.5-py3-none-any.whl

Download URL goldretriever-0.1.5-py3-none-any.whl
Size 90.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e8fcff11444c0f9deea60200acc6714511afff9155ea551bdc9f73acd5ce0d96
BLAKE2b-256 checksum
How to use checksums
e13705a9a534a56fbde47b294d6d7fac7624ebc89ecd99bc6275c92626c0d679
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.17

Release history Release notifications | RSS feed

This release

0.1.5 This release

2 release files

0.1.4

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page