LLMSERP
searchALL
imageIMAGES
videocamVIDEOS
shopping_cartSHOPPING
TOOLS
About 12 results (0.41 seconds)
Jina AI is an open-source neural search company. We build the next generation search for unstructured data. Our mission is to enable developers to build AI-powered search applications.
I'm sorry, but there is no Wikipedia article about "Jina AI". Perhaps you meant the name "Jina" which is a name of Indian origin.
Jina AI - Build Neural Search Applications with Python. In this video, we will build a neural search application with Jina AI.
Jina AI, a San Francisco-based startup, has raised $30 million in a series B funding round. The round was led by GGV Capital and saw participation from Mango Capital, SAP.iO Fund, and others. Jina AI offers an open-source neural search platform that lets developers build search applications for unstructured data.
Jina AI is a San Francisco-based company that offers a neural search platform for developers. The company's platform allows developers to build search applications for unstructured data.
Read writing from Jina AI on Medium. Every day, Jina AI and thousands of other voices read, write, and share important stories on Medium.
Learn about working at Jina AI. Join LinkedIn today for free. See who you know at Jina AI, leverage your professional network, and get hired.
Jina is a neural search framework that empowers developers to build search applications for unstructured data.
Jina AI (@JinaAI_). We build the next generation search for unstructured data. Open source neural search. San Francisco, CA. jina.ai Joined July 2019.
LLMSERP
1
2
3
4
5
6
7
8
9
10
navigate_next
question_answer
什麼是 SERP？
keyboard_arrow_down
question_answer
那麼所有搜索結果都是由 LLM 生成的嗎？
keyboard_arrow_down
question_answer
為什麼搜索結果中有些 URL 損壞並導致 404 頁面？
keyboard_arrow_down
question_answer
那麼為什麼有些 URL 是真實的並且會引導至實際的頁面？
keyboard_arrow_down
question_answer
我可以通過 API 調用它嗎？
keyboard_arrow_down
question_answer
但是如果所有搜索結果都是假的，那麼這個演示或 API 有什麼意義呢？
keyboard_arrow_down
question_answer
它是開源的嗎？
keyboard_arrow_down
速率限制
速率限制通過三種方式跟蹤：RPM（每分鐘請求數）和TPM（每分鐘詞元數）。限制按 IP/API 密鑰強制執行，當首先達到 RPM 或 TPM 閾值時，將觸發限制。當您在請求標頭中提供 API 密鑰時，我們會按密鑰而不是 IP 地址跟蹤速率限制。
| 產品 | API端口 | 描述arrow_upward | 無 API 密鑰key_off | 使用 API 密鑰key | 帶有高級 API 密鑰key | 平均延遲 | 詞元使用計數 | 請求類型 | |
|---|---|---|---|---|---|---|---|---|---|
| 讀取器 API | https://r.jina.ai | 將 URL 轉換為大模型友好文本 | 20 RPM | 500 RPM | trending_up5000 RPM | 7.9s | 以輸出響應中的詞元數量為準。 | GET/POST | |
| 讀取器 API | https://s.jina.ai | 搜索網絡並將結果轉換為大模型友好文本 | block | 100 RPM | trending_up1000 RPM | 2.5s | 每個請求都需要固定數量的詞元，從 10000 個詞元開始 | GET/POST | |
| 深度搜索 | https://deepsearch.jina.ai/v1/chat/completions | 推理、搜索和迭代以找到最佳答案 | block | 50 RPM | 500 RPM | 56.7s | 統計整個過程中詞元的總數。 | POST | |
| 向量模型API | https://api.jina.ai/v1/embeddings | 將文本/圖片轉為定長向量 | block | 500 RPM & 1,000,000 TPM | trending_up2,000 RPM & 5,000,000 TPM | ssid_chart 取決於輸入大小 help | 以輸入請求中的詞元數量為準。 | POST | |
| 重排器 API | https://api.jina.ai/v1/rerank | 按查詢對文檔進行精排 | block | 500 RPM & 1,000,000 TPM | trending_up2,000 RPM & 5,000,000 TPM | ssid_chart 取決於輸入大小 help | 以輸入請求中的詞元數量為準。 | POST | |
| 分類器 API | https://api.jina.ai/v1/train | 使用訓練樣本訓練分類器 | block | 20 RPM & 200,000 TPM | 60 RPM & 1,000,000 TPM | ssid_chart 取決於輸入大小 | 詞元計數為：輸入詞元 × 迭代次數 | POST | |
| 分類器 API (少量樣本) | https://api.jina.ai/v1/classify | 使用經過訓練的少樣本分類器對輸入進行分類 | block | 20 RPM & 200,000 TPM | 60 RPM & 1,000,000 TPM | ssid_chart 取決於輸入大小 | 詞元計數為：輸入詞元 | POST | |
| 分類器 API (零樣本) | https://api.jina.ai/v1/classify | 使用零樣本分類對輸入進行分類 | block | 200 RPM & 500,000 TPM | 1,000 RPM & 3,000,000 TPM | ssid_chart 取決於輸入大小 | 詞元計數為：輸入詞元 加 標籤詞元 | POST | |
| 切分器 API | https://api.jina.ai/v1/segment | 對長文本進行分詞分句 | 20 RPM | 200 RPM | 1,000 RPM | 0.3s | 詞元不計算使用量。 | GET/POST |
