{"id":15157877,"url":"https://github.com/comhendrik/vectormatch","last_synced_at":"2026-02-17T07:37:44.891Z","repository":{"id":256753312,"uuid":"856322807","full_name":"comhendrik/vectorMatch","owner":"comhendrik","description":"Dockerized application that embeds text in a pgvecto.rs database and retrieves data with a similarity search to generate a response with an llm from ollama.","archived":false,"fork":false,"pushed_at":"2024-12-01T09:32:15.000Z","size":32,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-20T07:32:57.423Z","etag":null,"topics":["docker","docker-compose","embeddings-similarity","nlp","ollama","pgvecto-rs","postgresql","python","vector","vector-database"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/comhendrik.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-09-12T11:40:29.000Z","updated_at":"2024-12-07T22:20:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"254f1f53-5ce1-47e9-8bd9-00c35b0d5e7d","html_url":"https://github.com/comhendrik/vectorMatch","commit_stats":{"total_commits":7,"total_committers":1,"mean_commits":7.0,"dds":0.0,"last_synced_commit":"6ad285aa32d7581f262068c19b650344f8157ada"},"previous_names":["comhendrik/vectormatch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/comhendrik/vectorMatch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/comhendrik%2FvectorMatch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/comhendrik%2FvectorMatch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/comhendrik%2FvectorMatch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/comhendrik%2FvectorMatch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/comhendrik","download_url":"https://codeload.github.com/comhendrik/vectorMatch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/comhendrik%2FvectorMatch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279019349,"owners_count":26086711,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-14T02:00:06.444Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["docker","docker-compose","embeddings-similarity","nlp","ollama","pgvecto-rs","postgresql","python","vector","vector-database"],"created_at":"2024-09-26T20:20:17.399Z","updated_at":"2025-10-14T15:43:39.889Z","avatar_url":"https://github.com/comhendrik.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Text Embedding and Search with PostgreSQL and Hugging Face in Docker\n\nThis project demonstrates a Python script that embeds text using a model from Hugging Face, stores the embeddings in PostgreSQL with the `pgvector` extension, and allows searching the database using regular text queries by comparing embeddings. After the data is retrieved an llm is used to generate a response with ollama. The Project is run with Docker Compose\n\n## Features\n- **Embeddings:** Use Hugging Face's transformers to embed input text.\n- **PostgreSQL with pgvector:** Store embeddings in a PostgreSQL database using the `pgvector` extension to perform vector-based searches.\n- **Search Functionality:** Retrieve database entries by comparing the input text's embedding to the stored embeddings.\n- **Docker Support:** Run the whole application with Docker compose\n- **Ollama:** Generate response based on local llm\n\n## Prerequisites\n\nMake sure you have the following installed:\n- **Docker**\n\n### Setup\n\nGet the project directory\n```\ngit clone https://github.com/comhendrik/vectorMatch.git\n```\nStart docker and go into the project directory and run the compose file\n```\ndocker compose up\n```\nWait for the script to be done, this can take a few minutes and then attach yourself to the vectorMatch container\n```\ndocker attach vectormatch-vector-match-1\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcomhendrik%2Fvectormatch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcomhendrik%2Fvectormatch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcomhendrik%2Fvectormatch/lists"}