{"id":21336214,"url":"https://github.com/sukhbinder/talk2doc","last_synced_at":"2025-03-16T01:44:22.068Z","repository":{"id":252638749,"uuid":"841013855","full_name":"sukhbinder/talk2doc","owner":"sukhbinder","description":"A tool to ask questions to documents in a set of PDFs","archived":false,"fork":false,"pushed_at":"2024-08-19T15:12:23.000Z","size":13,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-22T14:41:40.651Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sukhbinder.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}},"created_at":"2024-08-11T11:41:03.000Z","updated_at":"2024-08-19T15:12:26.000Z","dependencies_parsed_at":"2024-08-12T00:16:40.810Z","dependency_job_id":null,"html_url":"https://github.com/sukhbinder/talk2doc","commit_stats":null,"previous_names":["sukhbinder/talk2doc"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukhbinder%2Ftalk2doc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukhbinder%2Ftalk2doc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukhbinder%2Ftalk2doc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sukhbinder%2Ftalk2doc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sukhbinder","download_url":"https://codeload.github.com/sukhbinder/talk2doc/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243814856,"owners_count":20352037,"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":"2024-11-21T23:51:44.901Z","updated_at":"2025-03-16T01:44:22.047Z","avatar_url":"https://github.com/sukhbinder.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# talk2doc\nA tool to ask questions to documents in a set of PDFs\n\nThis works with ollama.\n\n## Installation\n\nTo install, run:\n\n```bash\npip install talk2doc\n```\nYou may need to adjust the version of `langchain_community` based on the actual library requirement.\n\n## Usage\n\nRun:\n\n```bash\ntalk2doc [model_name] [-p PDF_FILES] [-s CHUNK_SIZE] [-o CHUNK_OVERLAP] [-k TOP_K]\n```\n\nReplace `[model_name]` with the name of an LLM model (e.g., \"mistral\", \"gemma\").\nReplace `PDF_FILES` with a list of paths to PDF files.\n\nOptional arguments:\n* `-s CHUNK_SIZE`: Chunk size. Default: 500.\n* `-o CHUNK_OVERLAP`: Chunk overlap. Default: 50.\n* `-k TOP_K`: Top K docs to return. Default: 6.\n\nExample usage:\n\n```bash\ntalk2doc mistral -p /path/to/pdfs.pdf -s 1000 -o 75 -k 10\n```\n\nThis will use the \"mistral\" model, load PDF files from `/path/to/pdfs.pdf`, split each document into chunks of size 1000 with overlap 75, and return up to 10 top matches for each question.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsukhbinder%2Ftalk2doc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsukhbinder%2Ftalk2doc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsukhbinder%2Ftalk2doc/lists"}