本接口用于调用OpenAPI接口,在企业知识引擎新增文档时将文件关联知识库。
请求方式:POST
请求地址: https://console.volcengine.com/cdp/api/v2/rag/file2document/convert
参数名称 | 参数值类型 | 参数示例 | 说明 |
|---|---|---|---|
embd_factory | string | VolcEngine | 选用的embd模型厂商 |
embd_name | String | Doubao-embedding | 选用的embd模型名称 |
file_ids | List | [3413] | 文件id,从上传文件接口返回值中获取 |
kb_ids | List | [323] | 要关联的知识库id |
parse_config | Config | {} | 解析设置 |
参数名称 | 参数值类型 | 参数示例 | 说明 |
|---|---|---|---|
auto_keywords | number | 0 | 在查询此类关键词时,为每个块提取 N 个关键词以提高其排名得分 |
auto_questions | number | 0 | 在查询此类问题时,为每个块提取 N 个问题以提高其排名得分 |
strategy | number | 2 | 0 - 基于plaintext切分 |
chunk_size | number | 512 | 每个块的字符长度 |
detect_pdf_table | bool | true | 是否识别pdf表格 |
page_size_limit | number | 1000 | pdf页数限制 |
merge_small_chunks | bool | true | 是否合并小chunk |
pdf_with_ocr | bool | true | 是否解析扫描件 |
doctree_with_outline | bool | true | 是否使用pdf的outline进行章节理解 |
to_md | bool | true | 是否以Markdown返回 |
md_collapsed | bool | false | Markdown是否折叠 |
detect_header | bool | true | excel解析是否开启表格识别 |
参数名称 | 参数类型 | 参数示例 | 说明 |
|---|---|---|---|
code | number | 0 | 0->成功 |
msg | string | "success" | 当code为非0是包含错误信息 |
data | List | [] | 关联成功的文档 |
参数名称 | 参数值类型 | 参数示例 | 说明 |
|---|---|---|---|
id | number | 1 | 文件 - 文档关联关系的id |
file_id | number | 1 | 文件id |
document_id | number | 1 | 文档id |
curl 'https://console.volcengine.com/cdp/api/v2/rag/file2document/convert' \ -H 'accept: application/json, text/plain, */*' \ -H 'accept-language: zh-CN,zh;q=0.9' \ -H 'content-language: cn' \ -H 'content-type: application/json' \ -b 'vcloudWebId=caaa960d-aa79-42f8-b610-20bcb16c48f5; monitor_huoshan_web_id=3748351128612115054; monitor_session_id=0711109975673790130; monitor_session_id_flag=1; user_locale=zh; volc_platform_clear_user_locale=1; s_v_web_id=mb4quj0s_UEqGmfK3_07RM_4UU0_8qVI_OnqT8iqP3CSP; signin_i18next=zh; connect.sid=s%3Ab090794a-37ba-4011-9e1d-88fe58f04a08.i%2B6ulo4J0W%2B4ANiwKr%2F67MBDRg7r2ZRCTVlnpMwCpwc; connect.sid=s%3Ab090794a-37ba-4011-9e1d-88fe58f04a08.i%2B6ulo4J0W%2B4ANiwKr%2F67MBDRg7r2ZRCTVlnpMwCpwc; userInfo=eyJhbGciOiJSUzI1NiIsImtpZCI6IjViZmU3Y2M2NGJjNDExZWY5NGU2ZThlYmQzMmVlNmUyIn0.eyJhY2NfaSI6MjEwMDA4OTg4NiwiYXVkIjpbInZvbGNlbmdpbmUiXSwiZXhwIjoxNzUwODM1MTgyLCJpIjoiZDQ2MWQ0NTgtOWZhZi00YmRiLThmNzgtNjBhN2FhNTNhOTQ5IiwiaWRfbiI6IndzbDExMjAxIiwibXNnIjpudWxsLCJzc19uIjoid3NsMTEyMDEiLCJ0IjoiQWNjb3VudCIsInRvcGljIjoic2lnbmluX3VzZXJfaW5mbyIsInZlcnNpb24iOiJ2MSIsInppcCI6IiJ9.iK59lQO8kevghUTkAI_AeZ3qf1TVoOGPxAQTvHBDxr4rEHU-zXHrVUO3UJANaQhEGLJ3Seykw7jAi91E6A3pJPFu3gLezdX6B7sBV5uBI92SlFyMSOlsyaaESp1tXrrl4vkg0Ja2Cd_MimaUE-Otea3qMtE388z73256s0aZkB6fTson-Ax71-w36bcny1PNXFRRIUE-Ns75s8KfYXUE_xvVCXMgqMeK81W3zAo72VPVZ_KhmlaqcXzL_HqLHN1O1wcmntg0oPIfxbWjtMqd7eyxJkVeDFt4IfxrNNj9wvMkW5lC_M5Zo3qmZpPwq6t3YLBDpwPGI5zp7u2u4mdYGQ; login_scene=11; csrfToken=b10e639ae00ba2d3093bc81ddbcba493; csrfToken=b10e639ae00ba2d3093bc81ddbcba493; __tea_cache_tokens_3569={%22web_id%22:%227508647195731183114%22%2C%22user_unique_id%22:%227508647195731183114%22%2C%22timestamp%22:1748243183973%2C%22_type_%22:%22default%22}; VOLCFE_im_uuid=1748243184026964694; digest=eyJhbGciOiJSUzI1NiIsImtpZCI6IjZjYmMxNjBhNGJjNDExZWY5NGU2ZThlYmQzMmVlNmUyIn0.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.dmCfO1MFLVymF4NJnOhauwh9S_xfzJME5LCPrBj6phs-fWg5sts_8Pv3O5bV1vVGS2oOQEuAKpodEIvtwvLKD7Ut3_Xebec0P2e8Xxvxo02aLmXx_z1yEEfmbPGgjfprDV8tpYFkJFInzGTCFRViZaqm7bSBtgDAOFCBpoNfLTVx-pbFOFoZtYdMfRA-KmLFhBahpwGyaWBr_Ixwnq6zsMnXWQpjAAvJVzI0SKW4WBLFYxGTNr9Z8J_50UB_Hgmd2NvezVGnHn_Uq6_kTuJZYachHXD8c4IOwXgRtN83J-7hdEvgwen_SdGsjXKAskJoCJVp_UUeUEjOGQzUmX7tNg; digest=eyJhbGciOiJSUzI1NiIsImtpZCI6IjZjYmMxNjBhNGJjNDExZWY5NGU2ZThlYmQzMmVlNmUyIn0.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.dmCfO1MFLVymF4NJnOhauwh9S_xfzJME5LCPrBj6phs-fWg5sts_8Pv3O5bV1vVGS2oOQEuAKpodEIvtwvLKD7Ut3_Xebec0P2e8Xxvxo02aLmXx_z1yEEfmbPGgjfprDV8tpYFkJFInzGTCFRViZaqm7bSBtgDAOFCBpoNfLTVx-pbFOFoZtYdMfRA-KmLFhBahpwGyaWBr_Ixwnq6zsMnXWQpjAAvJVzI0SKW4WBLFYxGTNr9Z8J_50UB_Hgmd2NvezVGnHn_Uq6_kTuJZYachHXD8c4IOwXgRtN83J-7hdEvgwen_SdGsjXKAskJoCJVp_UUeUEjOGQzUmX7tNg; AccountID=2100089886; AccountID=2100089886' \ -H 'origin: https://console.volcengine.com' \ -H 'priority: u=1, i' \ -H 'referer: https://console.volcengine.com/cdp/knowledge-base/1010249/knowledge/create?id=323' \ -H 'sec-ch-ua: "Chromium";v="133", "Not(A:Brand";v="99"' \ -H 'sec-ch-ua-mobile: ?0' \ -H 'sec-ch-ua-platform: "macOS"' \ -H 'sec-fetch-dest: empty' \ -H 'sec-fetch-mode: cors' \ -H 'sec-fetch-site: same-origin' \ -H 'user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36' \ -H 'x-org: xx' \ -H 'x-tenant: xx' \ -H 'X-User: xx' \ -H 'Authorization: Bearer xx' \ --data-raw '{"embd_factory":"VolcEngine","embd_name":"Doubao-embedding","file_ids":[3413],"kb_ids":[323],"parser_config":{"auto_keywords":0,"auto_questions":0,"strategy":2,"chunk_size":512,"detect_pdf_table":true,"page_size_limit":1000,"merge_small_chunks":true,"pdf_with_ocr":true,"doctree_with_outline":true,"to_md":true,"md_collapsed":false,"detect_header":true},"source_type":"lark"}'