{"id":30863160,"url":"https://github.com/mlang/llm-embed-proxy","last_synced_at":"2025-09-07T18:07:11.484Z","repository":{"id":303489102,"uuid":"1015642531","full_name":"mlang/llm-embed-proxy","owner":"mlang","description":"Proxy for similarity search over visited pages","archived":false,"fork":false,"pushed_at":"2025-07-17T20:47:50.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-07-17T22:57:49.341Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/mlang.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":"2025-07-07T20:18:58.000Z","updated_at":"2025-07-17T20:47:53.000Z","dependencies_parsed_at":"2025-07-08T00:10:25.327Z","dependency_job_id":"e8458bde-57ba-44b3-b345-4fbef11eb951","html_url":"https://github.com/mlang/llm-embed-proxy","commit_stats":null,"previous_names":["mlang/llm-mitm-embed","mlang/llm-embed-proxy"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mlang/llm-embed-proxy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-embed-proxy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-embed-proxy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-embed-proxy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-embed-proxy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlang","download_url":"https://codeload.github.com/mlang/llm-embed-proxy/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-embed-proxy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274073753,"owners_count":25217774,"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":"2025-09-07T02:00:09.463Z","response_time":67,"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":[],"created_at":"2025-09-07T18:07:07.710Z","updated_at":"2025-09-07T18:07:11.065Z","avatar_url":"https://github.com/mlang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# llm-embed-proxy\n\nA proxy that embeds every web page you visit and lets you run similarity searches.\n\n1. Each successful **HTTP GET 200** response (except for localhost) is re-fetched from [pure.md](https://pure.md/) to obtain clean Markdown.\n2. The cleaned text is embedded through [llm](https://github.com/simonw/llm).\n3. A minimal Flask UI provides search and cached-page views.\n\n## Installation\n\nThis is not a stand-alone program.  It is a plugin for [llm](https://github.com/simonw/llm).  If you are not using `llm` yet, install it with `pipx` first.\n\n```bash\npipx install llm\n```\n\nNow you can install this plugin:\n\n```bash\nllm install git+https://github.com/mlang/llm-embed-proxy\n```\n\nTo be able to run a local embedding model, you need to install the `llm-sentence-transformers` plugin and register/download a model.  This step is optional if you happen to have an OpenAI API key and want to use their embedding endpoint.\n\n```bash\nllm install llm-sentence-transformers\nllm sentence-transformers register Qwen/Qwen3-Embedding-0.6B\n```\n\n## Running\n\n```bash\nllm embed-proxy --model sentence-transformers/Qwen/Qwen3-Embedding-0.6B\n```\n\nPoint your browser/system proxy to `localhost:8080` and visit `http://localhost:8080/` to search.\n\n### TLS Certificate\n\n`llm-embed-proxy` uses [mitmproxy](https://mitmproxy.org/) under the hood.\nIf you haven't used mitmproxy in the past, the first time you launch `llm embed-proxy` `mitmproxy` will generate a CA certificate in `~/.mitmproxy/`.\nTo avoid certificate warnings, you can add the mitmproxy CA certificate to your system.\n\nHere is how it would work on a Debian system:\n\n```bash\nsudo cp ~/.mitmproxy/mitmproxy-ca-cert.pem /usr/local/share/ca-certificates/mitmproxy-ca-cert.crt\nsudo /sbin/update-ca-certificates\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlang%2Fllm-embed-proxy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlang%2Fllm-embed-proxy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlang%2Fllm-embed-proxy/lists"}