{"id":23692678,"url":"https://github.com/jmservera/aithena","last_synced_at":"2026-04-20T01:04:06.245Z","repository":{"id":181702002,"uuid":"667170182","full_name":"jmservera/aithena","owner":"jmservera","description":"A system to extract knowledge from books","archived":false,"fork":false,"pushed_at":"2025-02-23T13:34:56.000Z","size":1715,"stargazers_count":0,"open_issues_count":17,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-22T09:40:36.196Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jmservera.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2023-07-16T21:43:59.000Z","updated_at":"2023-07-16T23:25:57.000Z","dependencies_parsed_at":"2023-11-15T09:25:21.774Z","dependency_job_id":"de33f6af-9107-4154-9b54-a125a43a24ed","html_url":"https://github.com/jmservera/aithena","commit_stats":null,"previous_names":["jmservera/aithena"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/jmservera/aithena","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmservera%2Faithena","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmservera%2Faithena/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmservera%2Faithena/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmservera%2Faithena/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jmservera","download_url":"https://codeload.github.com/jmservera/aithena/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmservera%2Faithena/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263446656,"owners_count":23467809,"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","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":"2024-12-30T03:34:51.317Z","updated_at":"2026-03-14T23:22:14.915Z","avatar_url":"https://github.com/jmservera.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Aithena\n\nA system to extract knowledge from books in pdf format. It uses the LLaMA embeddings\nto generate a vector database of the books in Qdrant. The system is built using\nDocker Compose with the following services:\n\n* [Qdrant](https://qdrant.tech/) - Vector database\n* [LLaMA.cpp Server](https://llama-cpp-python.readthedocs.io/en/latest/) - Embeddings\n* [LLaMA model](https://huggingface.co/openlm-research/open_llama_7b) - Embeddings model: \nyou can download the model and then generate the bin file running the llama-base\ncontainer `docker exec -it aithena-llama-base-1 python3 convert.py models/7B`.\n* A document lister and document indexer that will go through all the pdf files\nstored in an Azure Storage account and index them in Qdrant.\n\n## Usage\n\nConfigure the volumes folders in the `docker-compose.yml` file.\n\nRun `docker-compose up` to start the system. The first time you run it, it will\nfail because you won't have the LLaMA model downloaded. You can download it from\nthe [Hugging Face model hub](https://huggingface.co/openlm-research/open_llama_7b)\nand then generate the bin file running the llama-base container `docker exec -it\naithena-llama-base-1 python3 convert.py models/7B`.\n\n\n# Reference\n\n* https://python.langchain.com/docs/ecosystem/integrations/llamacpp\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmservera%2Faithena","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjmservera%2Faithena","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmservera%2Faithena/lists"}