Vellum - 用于构建优秀人工智能应用的开发者平台
羊皮纸游乐场：为即时工程师提供超能力
- 并排比较提示、模型，甚至包括LLM提供商
- 策划一个测试用例库，以评估提示的效果
- 使用行业标准的机器学习指标（Bleu、Meteor、Levenshtein距离、语义相似度）定量评估你的提示输出
羊皮纸管理：自信地在生产中迭代模型
- 简单的API接口，代理请求到任何模型提供商
- 回测和版本控制
- 对所有输入和输出的可观察性；UI和API用于提交显式或隐式用户反馈
羊皮纸搜索：在LLM应用中使用你的专有数据
- 强大的API端点，用于提交“文本语料库”以进行查询
- 可配置的分块和语义搜索策略
- 能够在运行时对文本语料库进行查询
羊皮纸优化：持续微调以提高质量和降低成本
- 被动地积累训练数据，以微调你自己的专有模型
- 在幕后更换模型提供商或参数-无需更改代码
我们是一支由麻省理工学院的工程师和麦肯锡的顾问组成的团队，在GPT-3发布后的3年里一直在构建应用程序。我们在MLOps领域也建立了类似的工具，并深刻体验到我们今天为客户解决的痛点。
我们相信人工智能是互联网以来最伟大的技术飞跃。我们的使命是通过将客户的原型推向生产，帮助公司采用人工智能。如果您有人工智能的用例，请与我们联系！
【Vellum】 Developer platform for building great AI applications
Vellum Playground: Super powers for prompt engineers
- Compare prompts, models, and even LLM providers side-by-side
- Curate a library of test cases to evaluate prompts against
- Quantitatively evaluate the output of your prompts using industry-standard ML metrics (Bleu, Meteor, Levenshtein distance, Semantic similarity)
Vellum Manage: Confidently iterate on models in production
- Simple API interface that proxies requests to any model provider
- Back-testing \u0026 version control
- Observability of all your inputs and outputs; UI \u0026 API to submit explicit or implicit user feedback
Vellum Search: Use your proprietary data in LLM applications
- Robust API endpoint to submit documents (“corpus of text”) for querying against
- Configurable chunking and semantic search strategies
- Ability to query against corpus of text at run time
Vellum Optimize: Continuously fine-tune to improve quality and lower cost
- Passively accumulate training data to fine-tune your own proprietary models
- Swap model providers or parameters under the hood – no code changes required
We’re a team of MIT engineers and McKinsey consultants who’ve been building apps on GPT-3 for 3 years since it first came out. We’ve built similar tools in MLOps for 4 years and have closely experienced the pain we’re solving for our customers today.
We believe that AI is the greatest technological leap since the internet. Our mission is to help companies adopt AI by taking their prototypes to production. If you have an AI use-case in mind, please reach out!
https://www.vellum.ai/
- 并排比较提示、模型，甚至包括LLM提供商
- 策划一个测试用例库，以评估提示的效果
- 使用行业标准的机器学习指标（Bleu、Meteor、Levenshtein距离、语义相似度）定量评估你的提示输出
羊皮纸管理：自信地在生产中迭代模型
- 简单的API接口，代理请求到任何模型提供商
- 回测和版本控制
- 对所有输入和输出的可观察性；UI和API用于提交显式或隐式用户反馈
羊皮纸搜索：在LLM应用中使用你的专有数据
- 强大的API端点，用于提交“文本语料库”以进行查询
- 可配置的分块和语义搜索策略
- 能够在运行时对文本语料库进行查询
羊皮纸优化：持续微调以提高质量和降低成本
- 被动地积累训练数据，以微调你自己的专有模型
- 在幕后更换模型提供商或参数-无需更改代码
我们是一支由麻省理工学院的工程师和麦肯锡的顾问组成的团队，在GPT-3发布后的3年里一直在构建应用程序。我们在MLOps领域也建立了类似的工具，并深刻体验到我们今天为客户解决的痛点。
我们相信人工智能是互联网以来最伟大的技术飞跃。我们的使命是通过将客户的原型推向生产，帮助公司采用人工智能。如果您有人工智能的用例，请与我们联系！
【Vellum】 Developer platform for building great AI applications
Vellum Playground: Super powers for prompt engineers
- Compare prompts, models, and even LLM providers side-by-side
- Curate a library of test cases to evaluate prompts against
- Quantitatively evaluate the output of your prompts using industry-standard ML metrics (Bleu, Meteor, Levenshtein distance, Semantic similarity)
Vellum Manage: Confidently iterate on models in production
- Simple API interface that proxies requests to any model provider
- Back-testing \u0026 version control
- Observability of all your inputs and outputs; UI \u0026 API to submit explicit or implicit user feedback
Vellum Search: Use your proprietary data in LLM applications
- Robust API endpoint to submit documents (“corpus of text”) for querying against
- Configurable chunking and semantic search strategies
- Ability to query against corpus of text at run time
Vellum Optimize: Continuously fine-tune to improve quality and lower cost
- Passively accumulate training data to fine-tune your own proprietary models
- Swap model providers or parameters under the hood – no code changes required
We’re a team of MIT engineers and McKinsey consultants who’ve been building apps on GPT-3 for 3 years since it first came out. We’ve built similar tools in MLOps for 4 years and have closely experienced the pain we’re solving for our customers today.
We believe that AI is the greatest technological leap since the internet. Our mission is to help companies adopt AI by taking their prototypes to production. If you have an AI use-case in mind, please reach out!
https://www.vellum.ai/
![$post['group']['name']](https://assets.fresns.cn/zhijie/groups/products/update-log.jpg)
发现创客新产品
0
