deepresearch-conversationDeep ReSearch Conversation is provided by Baidu for multi-round streaming conversations with "Deep Research" agents. "In-depth research" is a long-process task involving multi-step reasoning and execution, which is different from the ordinary "question-and-answer". A dialogue that requires the user to repeatedly verify and correct it until a satisfactory answer is reached.
Install via ClawdBot CLI:
clawdbot install ide-rea/deepresearch-conversationThis skill allows OpenClaw agents to conduct in-depth research discussions with users on a given topic. The API Key is automatically loaded from the OpenClaw config โ no manual setup is needed.
| name | path | description |
|------------|---------------------------------|---------------------------------------|
|DeepresearchConversation|/v2/agent/deepresearch/run|Multi-round streaming deep research conversation (via Python script)|
|ConversationCreate|/v2/agent/deepresearch/create|Create a new conversation session, returns conversation_id|
|FileUpload|/v2/agent/file/upload|Upload a file for the conversation|
|FileParseSubmit|/v2/agent/file/parse/submit|Submit an uploaded file for parsing|
|FileParseQuery|/v2/agent/file/parse/query|Query the status of a file parsing task|
conversation_id.conversation_id to upload files.file_id.query, conversation_id, and file_ids.conversation_id in all subsequent calls.interrupt_id (for "demand clarification" or "outline confirmation"), the next call must include that interrupt_id.structured_outline, present it to the user for confirmation/modification, then pass the final outline in the next call.no parameters
curl -X POST "https://qianfan.baidubce.com/v2/agent/deepresearch/create" \
-H "X-Appbuilder-From: openclaw" \
-H "Authorization: Bearer $BAIDU_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'agent_code: Fixed value "deepresearch" (required)conversation_id: From ConversationCreate response (required)file: Local file binary (mutually exclusive with file_url). Max 10 files. Supported formats:file_url: Public URL of the file (mutually exclusive with file)curl -X POST "https://qianfan.baidubce.com/v2/agent/file/upload" \
-H "Authorization: Bearer $BAIDU_API_KEY" \
-H "Content-Type: multipart/form-data" \
-H "X-Appbuilder-From: openclaw" \
-F "agent_code=deepresearch" \
-F "conversation_id=$conversation_id" \
-F "file=@local_file_path"curl -X POST "https://qianfan.baidubce.com/v2/agent/file/upload" \
-H "Authorization: Bearer $BAIDU_API_KEY" \
-H "Content-Type: multipart/form-data" \
-H "X-Appbuilder-From: openclaw" \
-F "agent_code=deepresearch" \
-F "conversation_id=$conversation_id" \
-F "file_url=$file_url"file_id: From FileUpload response (required)curl -X POST "https://qianfan.baidubce.com/v2/agent/file/parse/submit" \
-H "Authorization: Bearer $BAIDU_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Appbuilder-From: openclaw" \
-d '{"file_id": "$file_id"}'task_id: From FileParseSubmit response (required)curl -X GET "https://qianfan.baidubce.com/v2/agent/file/parse/query?task_id=$task_id" \
-H "Authorization: Bearer $BAIDU_API_KEY" \
-H "X-Appbuilder-From: openclaw"query: The user's question or research topic (required)conversation_id: Optional on first call (auto-generated). Required on subsequent calls.file_ids: List of parsed file IDs (optional, only when discussing files)interrupt_id: Required when responding to "demand clarification" or "outline confirmation" from previous round. Found in content.text.data of the previous SSE response.structured_outline: The research report outline. Required on subsequent calls if the previous round generated one. Structure:{
"title": "string",
"locale": "string",
"description": "string",
"sub_chapters": [
{
"title": "string",
"locale": "string",
"description": "string",
"sub_chapters": []
}
]
}version: "Lite" (faster, within 10 min) or "Standard" (deeper, slower). Default: "Standard".python3 scripts/deepresearch_conversation.py '{"query": "your question here", "version": "Standard"}'python3 scripts/deepresearch_conversation.py '{"query": "the question", "file_ids": ["file_id_1"], "interrupt_id": "interrupt_id", "conversation_id": "conversation_id", "structured_outline": {"title": "Report Title", "locale": "zh", "description": "desc", "sub_chapters": [{"title": "Chapter 1", "locale": "zh", "description": "chapter desc", "sub_chapters": []}]}, "version": "Standard"}'Generated Mar 1, 2026
Researchers can use this skill to iteratively develop and refine academic papers, uploading draft documents, receiving structured outlines, and incorporating feedback through multi-round conversations to produce well-organized research content.
Business analysts can upload market data files, such as spreadsheets and PDF reports, to generate in-depth market analysis reports, with the agent assisting in structuring findings and validating insights through interactive dialogue.
Legal professionals can upload contracts or case files for parsing, then engage in conversations to clarify legal terms, generate summaries, and outline key points, streamlining document analysis and client consultations.
Software developers and technical writers can upload code snippets or specifications, using the skill to create detailed technical documentation, with iterative feedback loops to ensure accuracy and completeness.
Healthcare providers can upload medical records or research papers to conduct in-depth analysis, generating structured reports on patient data or clinical studies through multi-step conversations that verify findings.
Offer this skill as a premium subscription service for businesses and researchers, providing access to advanced deep research capabilities with tiered pricing based on usage volume and file processing limits.
License the skill's APIs to third-party platforms, such as content management systems or educational tools, charging per API call or file upload, enabling scalable monetization through developer partnerships.
Provide tailored consulting services to large enterprises, integrating the skill into internal workflows for specific use cases like compliance reporting or R&D, with revenue from one-time setup fees and ongoing support contracts.
๐ฌ Integration Tip
Ensure the BAIDU_API_KEY is securely configured in the environment and handle SSE streaming responses properly to maintain conversation state across rounds.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.