Orkas Orkas
Download GitHub
More use cases: Deep research Chat with documents Make videos SEO & GEO Write code Build apps
Home Use cases Chat with Documents
Chat with Documents

Chat with your PDFs and
get cited answers.
Converse com seus PDFs e
obter respostas citadas.
与你的 PDF 对话,
获得带引用的答案。
あなたの PDF と対話して、
引用付きの回答を。

Add your PDFs and documents to your Library, then just ask. Orkas runs semantic search across your files and answers grounded in your own documents, with citations back to the source chunks — local-first, your own model keys, never proxied.Adicione seus PDFs e documentos à sua Biblioteca e é só pedir. Orkas executa pesquisa semântica em seus arquivos e respostas baseadas em seus próprios documentos, com citações de volta aos blocos de origem – local-first, suas próprias chaves de modelo, nunca passa por proxy. 把你的 PDF 和文档加入资料库(Library),然后开问。Orkas 对你的文件做语义检索,给出基于你自己文档、并附带出处片段引用的答案——本地优先,使用你自己的模型密钥,绝不中转。 あなたの PDF や文書をライブラリに追加して、あとは質問するだけ。Orkas がファイル全体をセマンティック検索し、あなた自身の文書に基づいて、出典チャンクへの引用付きで回答します——ローカルファースト、あなた自身のモデルキーで、決してプロキシしません。

Runs on your machineSearches your LibraryBYO LLM · never proxied
What you can ask

Talk to a whole stack of documents

Point Orkas at the files you already have — PDFs, papers, manuals, contracts — and ask questions across all of them at once.

Ask across a folder of PDFs

Add a stack of PDFs to your Library and get cited answers that draw from every file at once.

  • kb_list
  • kb_search

Find the clause in a long contract

Ask in plain language; semantic search surfaces the relevant passage and links back to the exact source chunk.

  • kb_search
  • kb_read

Summarize & compare papers

Compare findings across several documents, surface agreements and gaps, and draft a literature review with sources.

  • kb_read
  • summarize

Source-grounded Q&A

Get answers that quote the document they came from — extracted straight from your PDFs and DOCX files.

  • stat_file
  • read_file
In one conversation

From a folder of PDFs to a cited answer

You ask the question; Orkas searches your Library and grounds every claim in your files — your documents stay on your machine by default.

Every answer links back to the source chunk
Chat with documents
Which of these contracts allows early termination?
O
Orkas
Semantic search over your Library — 9 chunks across 4 files. skill: kb_search
O
Orkas
2 contracts include a termination-for-convenience clause — cited [MSA_AcmeCorp.pdf §11.2] · [Vendor_NDA.pdf §7].
How it works

Four moves, no config

01

Add your documents

Drop PDFs and files into your local Library.

02

Ask the question

“Find the clause”, “summarize these papers”, “what do they say about X”.

03

Check the citations

Every claim links back to the source chunk and file.

04

Keep asking

Follow up across the same Library — the index stays on your machine.

Safe with your documents

Your documents stay on your machine by default

Local-first

The source files and the vector index live on your machine — only the model API call goes out.

Grounded, not guessed

Answers cite the source chunk they came from, so you can verify before you rely on it.

BYO keys, never proxied

Use your own OpenAI / Claude / Gemini key; traffic goes direct.

See security →
FAQ

Chat-with-documents questions

Can Orkas chat with my PDFs and documents?O Orkas pode conversar com meus PDFs e documentos? Orkas 能与我的 PDF 和文档对话吗? Orkas は私の PDF や文書と対話できますか?

Yes. Add your PDFs and documents to your Library; Orkas runs semantic search across them and answers your questions grounded in those files, citing the source chunks it used — all on your machine, using your own LLM key.Sim. Adicione seus PDFs e documentos à sua Biblioteca; Orkas executa uma pesquisa semântica neles e responde às suas perguntas com base nesses arquivos, citando os pedaços de origem que usou – tudo em sua máquina, usando sua própria chave LLM. 可以。把你的 PDF 和文档加入资料库(Library);Orkas 对它们做语义检索,基于这些文件回答你的问题,并引用它用到的出处片段——全程在你的机器上,使用你自己的 LLM 密钥。 はい。あなたの PDF や文書をライブラリに追加してください。Orkas はそれらをセマンティック検索し、それらのファイルに基づいて質問に答え、使用した出典チャンクを引用します——すべてあなたのマシン上で、あなた自身の LLM キーを使って行われます。

Where are my documents stored?Onde meus documentos são armazenados? 我的文档存在哪里? 私の文書はどこに保存されますか?

By default your documents stay on your machine — the source files and the vector index are local-first — and your keys and model traffic never go through Orkas, so only the API call to your own provider leaves and it's never proxied. If you turn on Lite's optional multi-device sync, the data you sync is stored on Orkas servers so it's available across devices; the free edition also sends limited usage analytics (usage metadata, not your content).Por padrão, seus documentos permanecem em sua máquina - os arquivos de origem e o índice vetorial são local-first - e suas chaves e tráfego de modelo nunca passam pelo Orkas, portanto, apenas a chamada de API para seu próprio provedor sai e nunca passa por proxy. Se você ativar a sincronização opcional de vários dispositivos do Lite, os dados sincronizados serão armazenados nos servidores Orkas para que fiquem disponíveis em todos os dispositivos; a edição gratuita também envia análises de uso limitadas (metadados de uso, não seu conteúdo). 默认情况下,你的文档都在本机——原始文件和向量索引都本地优先——模型 Key 与模型流量始终不经过 Orkas,所以只有发往你自己模型提供商的 API 调用会发出,且绝不被代理。若开启 Lite 的多端同步,同步的数据会存到 Orkas 以便跨设备使用;基础版还会采集有限的使用数据(使用元数据,并非你的内容)。 既定では、あなたの文書はマシン上にとどまり——ソースファイルとベクトルインデックスはローカルファーストで——キーとモデルのトラフィックは Orkas を経由しないため、送出されるのは自分のプロバイダーへの API 呼び出しだけで、決してプロキシされません。Lite の任意の複数端末同期を有効にすると、同期したデータは複数端末で使えるよう Orkas のサーバーに保存されます。無料版では限定的な利用解析(コンテンツではなく利用メタデータ)も送信されます。

Are the answers grounded, and do I get citations?As respostas são fundamentadas e recebo citações? 这些答案有据可依吗?我会得到引用吗? 回答には根拠があり、引用は得られますか?

Yes. Answers are grounded in your documents and cite the source chunks the search hit, so you can open the original passage and verify it before you rely on it.Sim. As respostas são baseadas em seus documentos e citam os trechos de origem encontrados na pesquisa, para que você possa abrir a passagem original e verificá-la antes de confiar nela. 是的。答案基于你自己的文档,并引用检索命中的出处片段,你可以打开原始段落、在依赖它之前自己核实。 はい。回答はあなたの文書に基づいており、検索でヒットした出典チャンクを引用するため、それに頼る前に元の箇所を開いて確認できます。

Is Orkas a private chat-with-PDF tool?Orkas é uma ferramenta de chat privado com PDF? Orkas 是私有的 PDF 对话工具吗? Orkas はプライベートな PDF 対話ツールですか?

Yes. Orkas can work as a private chat-with-documents assistant: your source files and local Library stay on your machine by default, you bring your own model key, and model traffic goes directly to your provider instead of through Orkas.Sim. Orkas pode funcionar como um assistente privado de chat com documentos: seus arquivos de origem e biblioteca local permanecem em sua máquina por padrão, você traz sua própria chave de modelo e o tráfego do modelo vai diretamente para seu provedor, em vez de passar por Orkas. 是的。Orkas 可以作为私有文档对话助手使用:原始文件和本地 Library 默认留在你的机器上,你使用自己的模型密钥,模型流量直接发往你的提供商,而不是经过 Orkas。 はい。Orkas はプライベートな文書対話アシスタントとして使えます。ソースファイルとローカル Library は既定であなたのマシン上に残り、自分のモデルキーを使い、モデル通信は Orkas を経由せずプロバイダーへ直接送られます。

Doing deep literature work? See the For Researchers use case. Need the privacy angle first? Read Private AI Assistant.

Put a team on your documents

Free, open source, runs on your machine.