https://github.com/saifk2049/uniqueseek
a personal project aimed at quickly looking at RAG and open source LLMS
https://github.com/saifk2049/uniqueseek
docker fastapi llm rag
Last synced: about 2 months ago
JSON representation
a personal project aimed at quickly looking at RAG and open source LLMS
- Host: GitHub
- URL: https://github.com/saifk2049/uniqueseek
- Owner: SaifK2049
- Created: 2025-02-02T21:16:59.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-02T22:06:03.000Z (over 1 year ago)
- Last Synced: 2025-03-29T10:15:25.369Z (about 1 year ago)
- Topics: docker, fastapi, llm, rag
- Language: Python
- Homepage:
- Size: 13.7 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
**UniqueSeek: An intuitive approach to finetuning LLM with plaintext files**
UniqueSeek is an amatuer project which aims to introduce a user friendly appraoch by simply allowing the addition of a txt file to the initial prompt using the deepseek-r1 model.
**Requirements**
Please make sure that you have the deepseek model installed within your system using Ollama
Step 1. **Downloading Ollama**
https://ollama.com/download
please follow the Ollama setup instructions in order to have it installed within your system
Step 2. **Downloading deepseek-r1**
this Project uses the deepseek-r1:7B model which takes into consideration the RAM and VRAM capabilites of our consumer grade electronics.
#in your powershell run the following
ollama serve
ollama run deepseek-r1
#to check if your file has been running correctly
ollama ps
#you should the see the following sample output
NAME ID SIZE MODIFIED
deepseek-r1:latest 0a8c26691023 4.7 GB 5 hours ago
Step 3. **Running docker file**
Go to the project directory; in the terminal run the following command:
docker build -t deepseek-image -f dockerfile.dockerfile
docker run deepseek-image