{"id":13543331,"url":"https://github.com/rlancemartin/auto-evaluator","last_synced_at":"2025-05-16T13:02:49.622Z","repository":{"id":153255561,"uuid":"628105790","full_name":"rlancemartin/auto-evaluator","owner":"rlancemartin","description":"Evaluation tool for LLM QA chains","archived":false,"fork":false,"pushed_at":"2023-05-10T02:00:18.000Z","size":45781,"stargazers_count":1062,"open_issues_count":2,"forks_count":95,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-10-30T00:31:50.434Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://autoevaluator.langchain.com/","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/rlancemartin.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}},"created_at":"2023-04-14T23:46:38.000Z","updated_at":"2024-10-29T00:31:48.000Z","dependencies_parsed_at":"2023-06-29T12:02:31.847Z","dependency_job_id":null,"html_url":"https://github.com/rlancemartin/auto-evaluator","commit_stats":null,"previous_names":["pineappleexpress808/auto-evaluator"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rlancemartin%2Fauto-evaluator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rlancemartin%2Fauto-evaluator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rlancemartin%2Fauto-evaluator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rlancemartin%2Fauto-evaluator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rlancemartin","download_url":"https://codeload.github.com/rlancemartin/auto-evaluator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254535803,"owners_count":22087398,"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":"2024-08-01T11:00:30.227Z","updated_at":"2025-05-16T13:02:49.603Z","avatar_url":"https://github.com/rlancemartin.png","language":"Python","funding_links":[],"categories":["精选开源项目合集","Open-source LLM-backed app evaluation products","Python","Tools"],"sub_categories":["GPT工具"],"readme":"# `Auto-evaluator` :brain: :memo:\n\n\u003e **Note**\n\u003e See the HuggingFace space for this app: https://huggingface.co/spaces/rlancemartin/auto-evaluator\n\n\u003e **Note**\n\u003e See the hosted app: https://autoevaluator.langchain.com/\n\n\u003e **Note**\n\u003e Code for the hosted app is also open source: https://github.com/langchain-ai/auto-evaluator\n\nThis is a lightweight evaluation tool for question-answering using Langchain to:\n\n- Ask the user to input a set of documents of interest\n\n- Apply an LLM (`GPT-3.5-turbo`) to auto-generate `question`-`answer` pairs from these docs\n\n- Generate a question-answering chain with a specified set of UI-chosen configurations\n\n- Use the chain to generate a response to each `question`\n\n- Use an LLM (`GPT-3.5-turbo`) to score the response relative to the `answer`\n\n- Explore scoring across various chain configurations\n\n**Run as Streamlit app**\n\n`pip install -r requirements.txt`\n\n`streamlit run auto-evaluator.py`\n\n**Inputs**\n\n`num_eval_questions` - Number of questions to auto-generate (if the user does not supply an eval set)\n\n`split_method` - Method for text splitting\n\n`chunk_chars` - Chunk size for text splitting\n \n`overlap` - Chunk overlap for text splitting\n  \n`embeddings` - Embedding method for chunks\n \n`retriever_type` - Chunk retrieval method\n\n`num_neighbors` - Neighbors for retrieval \n\n`model` - LLM for summarization of retrieved chunks \n\n`grade_prompt` - Prompt choice for model self-grading\n\n**Blog**\n\nhttps://blog.langchain.dev/auto-eval-of-question-answering-tasks/\n\n**UI**\n\n![image](https://user-images.githubusercontent.com/122662504/233218347-de10cf41-6230-47a7-aa9e-8ab01673b87a.png)\n\n**Disclaimer**\n\n```You will need an OpenAI API key with access to `GPT-4` and an Anthropic API key to take advantage of all of the default dashboard model settings. However, additional models (e.g., from Hugging Face) can be easily added to the app.```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frlancemartin%2Fauto-evaluator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frlancemartin%2Fauto-evaluator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frlancemartin%2Fauto-evaluator/lists"}