{"id":15663083,"url":"https://github.com/danielfrg/gcp-llm-retrieval-augmentation","last_synced_at":"2025-10-14T05:30:47.909Z","repository":{"id":184259976,"uuid":"671581049","full_name":"danielfrg/gcp-llm-retrieval-augmentation","owner":"danielfrg","description":"A retrieval augmentation LLM demo in GCP","archived":true,"fork":false,"pushed_at":"2024-02-23T07:09:46.000Z","size":331,"stargazers_count":19,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-04T13:35:26.799Z","etag":null,"topics":["gcp","langchain","llm","matching-engine","vertex-ai"],"latest_commit_sha":null,"homepage":"https://llmops-demos-frg.web.app","language":"Jupyter Notebook","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/danielfrg.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}},"created_at":"2023-07-27T16:38:32.000Z","updated_at":"2024-09-20T10:01:09.000Z","dependencies_parsed_at":"2024-02-23T08:26:28.774Z","dependency_job_id":"a0692397-fe17-4a76-8bbb-8b878cc01775","html_url":"https://github.com/danielfrg/gcp-llm-retrieval-augmentation","commit_stats":null,"previous_names":["danielfrg/gcp-langchain-retrieval-augmentation","danielfrg/gcp-llm-retrieval-augmentation"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielfrg%2Fgcp-llm-retrieval-augmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielfrg%2Fgcp-llm-retrieval-augmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielfrg%2Fgcp-llm-retrieval-augmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielfrg%2Fgcp-llm-retrieval-augmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danielfrg","download_url":"https://codeload.github.com/danielfrg/gcp-llm-retrieval-augmentation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236446698,"owners_count":19150125,"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":["gcp","langchain","llm","matching-engine","vertex-ai"],"created_at":"2024-10-03T13:35:26.910Z","updated_at":"2025-10-14T05:30:42.605Z","avatar_url":"https://github.com/danielfrg.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM retrieval augmentation in Google Cloud\n\nThis demo features\n[GCP Vector Search](https://cloud.google.com/vertex-ai/docs/matching-engine/overview) and\n[VertexAI PaLM](https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/api-quickstart)\nto combine the functionality of retrieval augmentation and conversational engines\nto create a question answering system where the user can ask a question and the\nLLM will use it's given context to answer the question.\n\nThe Dataset used is the\n[Stanford Question Answering Dataset (SQuAD)](https://huggingface.co/datasets/squad)\n, a reading comprehension dataset, consisting of questions posed by\ncrowdworkers on a set of Wikipedia articles.\n\nThe demo can be accessed [here](https://llmops-demos-frg.web.app).\n\n## Services used\n\n![Architecture](/web/public/arch.jpg)\n\n- [VertexAI Vector Search](https://cloud.google.com/vertex-ai/docs/matching-engine/overview): ANN Similarity Seach\n- [VertexAI PaLM](https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/api-quickstart): Conversational Engine\n- [Cloud Run](https://cloud.google.com/run): Hosting of the API\n- [Firestore](https://cloud.google.com/firestore): Document Database\n- [Firebase](https://firebase.google.com): Frontend hosting\n- [Cloud Build](https://cloud.google.com/build): CI/CD\n\nFrameworks:\n\n- [LangChain](https://python.langchain.com/): Framework for creating conversational agent and retrieval augmentation\n- [Tensorflow Hub](https://www.tensorflow.org/hub):\n  Embeddings\n\n## Prerequisites\n\n- [Terraform](https://cloud.google.com/docs/terraform)\n- A GCP project created\n\n## Docs\n\n1. [Infrastructure and Vector Search Setup](/docs/1_matching_engine.md):\n   Setup the required infrastructure using Terraform and create\n   the Vector Search index\n2. [Create embeddings](/docs/2_create_embeddings.md): Generate the embeddings for the documents and index them in\n   Vector Search\n3. [Firestore](/docs/3_firestore.md): Index the documents in Firestore\n4. [LangChain Retriever and Agent](/docs/4_agent.md): Create a LangChain retriever and conversational agent\n5. [Cloud Run](/docs/5_cloud_run.md): Grab all the code, package it and deploy the API to Cloud Run\n6. [Firebase WebUI](/docs/6_firebase.md): Create the Web app\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielfrg%2Fgcp-llm-retrieval-augmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanielfrg%2Fgcp-llm-retrieval-augmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielfrg%2Fgcp-llm-retrieval-augmentation/lists"}