Back to Details

pinecone-assistant

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Pinecone Assistant

Pinecone Assistant

Pinecone Assistant is a fully managed RAG service. Upload documents, ask questions, get cited answers. No embedding pipelines or infrastructure required.
All scripts are in 
scripts/
relative to this skill directory. Run with: 
uv run scripts/script_name.py [arguments]
<<clarify_style>>
Pinecone Assistant 是一种完全托管的 RAG 服务。上传文档、提出问题并获得带引用的答案，无需 embedding 管线或基础设施。
本 skill 目录下的所有脚本均位于 
scripts/
中。 运行方式：
uv run scripts/script_name.py [arguments]
<<clarify_style>>

Operations

操作

What to doScriptKey args
Create an assistant
scripts/create.py
--name
--instructions
--region
Upload files
scripts/upload.py
--assistant
--source
--patterns
Sync files (incremental)
scripts/sync.py
--assistant
--source
--delete-missing
--dry-run
Chat / ask a question
scripts/chat.py
--assistant
--message
Get context snippets
scripts/context.py
--assistant
--query
--top-k
List assistants
scripts/list.py
--files
--json
For full workflow details on any operation, read the relevant file in 
references/
.
要执行的操作脚本关键参数
创建 Assistant
scripts/create.py
--name
--instructions
--region
上传文件
scripts/upload.py
--assistant
--source
--patterns
同步文件（增量）
scripts/sync.py
--assistant
--source
--delete-missing
--dry-run
聊天 / 提出问题
scripts/chat.py
--assistant
--message
获取上下文片段
scripts/context.py
--assistant
--query
--top-k
列出 Assistant
scripts/list.py
--files
--json
如需了解任一操作的完整工作流，请阅读 
references/
中的相关文件。

Natural Language Recognition

自然语言识别

Proactively handle these patterns without requiring explicit commands:
Create: "create an assistant", "make an assistant called X", "set up an assistant for my docs" → See references/create.md
Upload: "upload my docs", "add files to my assistant", "index my documentation" → See references/upload.md
Sync: "sync my docs", "update my assistant", "keep assistant in sync", "refresh from ./docs" → See references/sync.md
Chat: "ask my assistant about X", "what does my assistant know about X", "chat with X" → See references/chat.md
Context: "search my assistant for X", "find context about X" → See references/context.md
List: "show my assistants", "what assistants do I have" → Run 
uv run scripts/list.py
无需用户明确输入命令，即可主动处理以下表达方式：
创建：“创建一个 Assistant”“创建一个名为 X 的 Assistant”“为我的文档设置一个 Assistant” → 参阅 references/create.md
上传：“上传我的文档”“向我的 Assistant 添加文件”“为我的文档建立索引” → 参阅 references/upload.md
同步：“同步我的文档”“更新我的 Assistant”“保持 Assistant 同步”“从 ./docs 刷新” → 参阅 references/sync.md
聊天：“向我的 Assistant 询问 X”“我的 Assistant 了解哪些关于 X 的内容”“与 X 聊天” → 参阅 references/chat.md
上下文：“在我的 Assistant 中搜索 X”“查找关于 X 的上下文” → 参阅 references/context.md
列表：“显示我的 Assistants”“我有哪些 Assistant” → 运行 
uv run scripts/list.py

Conversation Memory

对话记忆

Track the last assistant used within the conversation:
  • When a user creates or first uses an assistant, remember its name
  • If user says "my assistant", "it", or "the assistant" → use the last one
  • Briefly confirm which assistant you're using: "Asking docs-bot..."
  • If ambiguous and multiple exist → ask the user to clarify
在对话中追踪最近使用的 Assistant：
  • 当用户创建或首次使用某个 Assistant 时，记住其名称
  • 如果用户说“我的 Assistant”“它”或“这个 Assistant”，则使用最近使用的 Assistant
  • 简要确认正在使用的 Assistant，例如：“正在向 docs-bot 提问……”
  • 如果存在歧义且有多个 Assistant，则请用户澄清

Multi-Step Requests

多步骤请求

Handle chained requests naturally. Example:
"Create an assistant called docs-bot, upload my ./docs folder, and ask what the main features are"
  1. uv run scripts/create.py --name docs-bot
  2. uv run scripts/upload.py --assistant docs-bot --source ./docs
  3. uv run scripts/chat.py --assistant docs-bot --message "what are the main features?"
自然地处理链式请求。例如：
“创建一个名为 docs-bot 的 Assistant，上传我的 ./docs 文件夹，并询问主要功能是什么”
  1. uv run scripts/create.py --name docs-bot
  2. uv run scripts/upload.py --assistant docs-bot --source ./docs
  3. uv run scripts/chat.py --assistant docs-bot --message "主要功能是什么？"

Prerequisites

前置条件