Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.9%) to scientific vocabulary
Keywords
Repository
Fluid Database
Basic Info
- Host: GitHub
- Owner: TheMind-AI
- License: other
- Language: Python
- Default Branch: main
- Homepage: https://themind.ai
- Size: 1.45 MB
Statistics
- Stars: 114
- Watchers: 3
- Forks: 8
- Open Issues: 1
- Releases: 0
Topics
Metadata Files
README.md
FluidDB
Self-Organizing Databases
Research repo for experimenting with the concept of a fluid database.
What is Fluid Database?
FluidDB (Fluid Database) is a concept for databases that dynamically update its schema based on the ingested data. It's here for you to build truly personalized AI agents by giving them memory.
LLM + FluidDB = Personalized AI
Key features: - Adaptive Schema: Automatically adjusts its structure based on the data being ingested. - Flexible Querying: Supports both traditional query languages and intuitive natural language queries. - Versatile Data Input: Enables data entry in natural language, as well as in semi-structured formats.
Want to see it in action? Check out the MIND Apps.
Roadmap
- [ ] FluidDB Client
- [ ] Databases Engine
- [ ] CLI
- [ ] Router
- [ ] Eval System
- [ ] Hosted Service
FluidDB Example
FluidDB saves unstructured data in a structured form. ```py
Saving a simple natural language statement into FluidDB
fluiddb.save(uid, "hey adam here and i like thinking about the roman empire")
FluidDB automatically updates its schema to reflect this new data:
json
{
"name": "Adam",
"interests": ["thinking about the Roman Empire"]
}
```
Further, FluidDB demonstrates its versatility with semi-structured data formats. For instance:
```py
Storing structured data like an email
email = {
"from": "david@themind.ai",
"to": "adam@themind.ai",
"subject": "Check this out",
"content": "Hi Adam, Hope this email finds you well ..."
}
fluiddb.save(uid, email)
FluidDB then incorporates this new information into its schema:
json
{
"name": "Adam",
"interests": ["thinking about the Roman Empire", "blue bottle"],
"email": [{
"from": "david@themind.ai",
"to": "adam@themind.ai",
"subject": "Check this out",
"content": "Hi Adam, Hope this email finds you well ..."
}]
}
```
Getting Started
bash
building...
Owner
- Name: TheMind
- Login: TheMind-AI
- Kind: organization
- Email: hello@themind.ai
- Location: United States of America
- Website: themind.ai
- Twitter: themind_ai
- Repositories: 1
- Profile: https://github.com/TheMind-AI
AI — Human Interaction
Citation (CITATION.cff)
cff-version: 0.0.1 message: "If you use this software, please cite it as below." title: "FluidDB" url: "https://github.com/themind-ai/fluid-db" authors: - family-names: "Zvada" given-names: "Adam" orcid: "https://orcid.org/0009-0001-5907-9513"
GitHub Events
Total
- Watch event: 3
Last Year
- Watch event: 3
Issues and Pull Requests
Last synced: almost 2 years ago
All Time
- Total issues: 1
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 1
- Total pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 1
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 1
- Pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- OmarHedeya95 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- backoff *
- fastapi *
- firebase-admin *
- genson *
- gunicorn *
- instructor ==0.4.2
- jsonpath-ng *
- openai ==1.3.7
- pydantic *
- python-dotenv *
- uvicorn *