{"data":{"slug":"venuv-langchain-semantic-search","name":"langchain_semantic_search","tagline":"Search and indexing your own Google Drive Files using GPT3, LangChain, and Python","github_url":"https://github.com/venuv/langchain_semantic_search","owner":"venuv","repo":"langchain_semantic_search","owner_avatar_url":"https://avatars.githubusercontent.com/u/1031925?v=4","primary_language":"Jupyter Notebook","stars":44,"forks":8,"topics":[],"archived":false,"github_pushed_at":"2023-02-07T11:42:25+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/venuv-langchain-semantic-search","markdown_url":"https://www.graphcanon.com/tools/venuv-langchain-semantic-search.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/venuv-langchain-semantic-search","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=venuv-langchain-semantic-search","description":"Search and indexing your own Google Drive Files using GPT3, LangChain, and Python","homepage_url":null,"license":null,"open_issues":0,"watchers":1,"ai_summary":null,"readme_excerpt":"## Search and indexing your own Google Drive Files using GPT3, LangChain, and Python.\n\nThe jupyter notebook included here (langchain_semantic_search.ipynb) will enable you to build a FAISS index on your document corpus of interest, and search it using semantic search. Details of this flowchart are described in https://medium.com/@venuv62/can-chatgpt-be-your-bff-code-companion-4375fd73ec3a. \n\n\n\n\nI've provided a test directory of Neuromodulation papers if you want to as a sample Drive folder to test against -  https://drive.google.com/drive/folders/1eIBnSO7MVOW9-BKPCJhs7JuBDRyXPOFC?usp=sharing. Since the code needs a Google Drive directory path (not an https URL) to work with, you will have to :\n- copy the contents of this directory into a GDrive subdirectory of your own\n- set the gdrive_path variable in the jupyter notebook appropriately\n- set the question within print_answer to 'is sleep a health epidemic' for instance, which should give you a non-null answer\n\nI will be working on a few enhancements to speed up the indexing (perhaps using a Vectorstore) and to optimize the query cost (using ideas from https://gpt-index.readthedocs.io/en/latest/how_to/cost_analysis.html)","github_created_at":"2023-02-07T06:43:55+00:00","created_at":"2026-07-11T10:52:43.285488+00:00","updated_at":"2026-07-11T10:52:52.226253+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"jupyter-notebook","name":"jupyter notebook"}],"trust":{"provenance":{"is_fork":false,"github_id":598462314,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T10:52:44.279Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1249,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:52:45.116Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T10:52:44.731Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-07-11T10:52:44.731Z"}}}}