quivr [Bug]: 羊驼嵌入的维度为1536,而预期的维度为4096,

mhd8tkvw  于 2个月前  发布在  其他
关注(0)|答案(6)|浏览(52)

发生了什么？
当我通过Ollama与新创建的大脑进行聊天时，出现了“不同向量维度”的错误。嵌入查询的预期维度为4096(chatgpt3.5-turbo-0125是正常的)。
相关日志输出

backend-core  | 2024-03-17 08:57:39,590:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,596:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations_user?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,601:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations?select=%2A&id=eq.b37a2275-61b3-460b-b4ab-94dfdf3642fb "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,606:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains_users?select=id%3Abrain_id%2C%20rights%2C%20brains%20%28id%3A%20brain_id%2C%20status%2C%20name%2C%20brain_type%2C%20description%29&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,611:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,617:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations_user?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:39,621:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations?select=%2A&id=eq.b37a2275-61b3-460b-b4ab-94dfdf3642fb "HTTP/1.1 200 OK"
backend-core  | INFO:     172.21.0.1:37134 - "GET /brains/b1c76842-fa7a-416e-b6a0-3f84fef9752f/ HTTP/1.1" 200 OK
backend-core  | INFO:     172.21.0.1:37134 - "OPTIONS /chat/6604e220-9b7d-4b82-b33f-fbd7038ec291/question/stream?brain_id=b1c76842-fa7a-416e-b6a0-3f84fef9752f HTTP/1.1" 200 OK
backend-core  | 2024-03-17 08:57:41,384:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,389:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations_user?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,392:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations?select=%2A&id=eq.b37a2275-61b3-460b-b4ab-94dfdf3642fb "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,395:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains_users?select=id%3Abrain_id%2C%20rights%2C%20brains%20%28id%3A%20brain_id%2C%20status%2C%20name%2C%20brain_type%2C%20description%29&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | [INFO] modules.chat.controller.chat_routes [chat_routes.py:228]: Creating question for chat 6604e220-9b7d-4b82-b33f-fbd7038ec291 with brain b1c76842-fa7a-416e-b6a0-3f84fef9752f of type <class 'uuid.UUID'>
backend-core  | 2024-03-17 08:57:41,399:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,403:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations_user?select=%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,406:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/integrations?select=%2A&id=eq.b37a2275-61b3-460b-b4ab-94dfdf3642fb "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,409:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains_users?select=id%3Abrain_id%2C%20rights%2C%20brains%20%28id%3A%20brain_id%2C%20status%2C%20name%2C%20brain_type%2C%20description%29&user_id=eq.39418e3b-0258-4452-af60-7acfcc1263ff&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,418:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/chat_history?select=%2A&chat_id=eq.6604e220-9b7d-4b82-b33f-fbd7038ec291&order=message_time "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,427:INFO - HTTP Request: GET http://host.docker.internal:54321/rest/v1/brains?select=id%3Abrain_id%2C%20name%2C%20%2A&brain_id=eq.b1c76842-fa7a-416e-b6a0-3f84fef9752f "HTTP/1.1 200 OK"
backend-core  | 2024-03-17 08:57:41,601:INFO - HTTP Request: POST http://host.docker.internal:54321/rest/v1/rpc/match_brain "HTTP/1.1 400 Bad Request"
backend-core  | INFO:     172.21.0.1:37134 - "POST /chat/6604e220-9b7d-4b82-b33f-fbd7038ec291/question/stream?brain_id=b1c76842-fa7a-416e-b6a0-3f84fef9752f HTTP/1.1" 500 Internal Server Error
backend-core  | ERROR:    Exception in ASGI application
backend-core  | Traceback (most recent call last):
backend-core  |   File "/usr/local/lib/python3.11/site-packages/uvicorn/protocols/http/h11_impl.py", line 408, in run_asgi
backend-core  |     result = await app(  # type: ignore[func-returns-value]
backend-core  |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/usr/local/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 69, in __call__
backend-core  |     return await self.app(scope, receive, send)
backend-core  |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/usr/local/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
backend-core  |     await super().__call__(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/applications.py", line 123, in __call__
backend-core  |     await self.middleware_stack(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 186, in __call__
backend-core  |     raise exc
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 164, in __call__
backend-core  |     await self.app(scope, receive, _send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/middleware/cors.py", line 91, in __call__
backend-core  |     await self.simple_response(scope, receive, send, request_headers=headers)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/middleware/cors.py", line 146, in simple_response
backend-core  |     await self.app(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
backend-core  |     await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
backend-core  |     raise exc
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
backend-core  |     await app(scope, receive, sender)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 758, in __call__
backend-core  |     await self.middleware_stack(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 778, in app
backend-core  |     await route.handle(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 299, in handle
backend-core  |     await self.app(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 79, in app
backend-core  |     await wrap_app_handling_exceptions(app, request)(scope, receive, send)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
backend-core  |     raise exc
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
backend-core  |     await app(scope, receive, sender)
backend-core  |   File "/usr/local/lib/python3.11/site-packages/starlette/routing.py", line 74, in app
backend-core  |     response = await func(request)
backend-core  |                ^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/usr/local/lib/python3.11/site-packages/fastapi/routing.py", line 278, in app
backend-core  |     raw_response = await run_endpoint_function(
backend-core  |                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/usr/local/lib/python3.11/site-packages/fastapi/routing.py", line 191, in run_endpoint_function
backend-core  |     return await dependant.call(**values)
backend-core  |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/code/modules/chat/controller/chat_routes.py", line 232, in create_stream_question_handler
backend-core  |     gpt_answer_generator = get_answer_generator(
backend-core  |                            ^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/code/modules/chat/controller/chat_routes.py", line 76, in get_answer_generator
backend-core  |     brain, metadata_brain = brain_service.find_brain_from_question(
backend-core  |                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/code/modules/brain/service/brain_service.py", line 109, in find_brain_from_question
backend-core  |     list_brains = vector_store.find_brain_closest_query(user.id, question)
backend-core  |                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
backend-core  |   File "/code/vectorstore/supabase.py", line 54, in find_brain_closest_query
backend-core  |     ).execute()
backend-core  |       ^^^^^^^^^
backend-core  |   File "/usr/local/lib/python3.11/site-packages/postgrest/_sync/request_builder.py", line 127, in execute
backend-core  |     raise APIError(r.json())
backend-core  | postgrest.exceptions.APIError: {'code': '22000', 'details': None, 'hint': None, 'message': 'different vector dimensions 1536 and 4096'}

Twitter / LinkedIn详细信息

  • 无响应*
quivr

6条答案

按热度按时间
xmjla07d

xmjla07d1#

嘿，@binhaoIsUsed,很高兴看到你回来！开始另一个挑战了吗？让我们一起解决这个问题。
你遇到的错误可能是由于 find_brain_closest_query 函数期望的向量维度与 Embeddings 示例生成的实际向量维度之间存在不匹配。find_brain_closest_query 函数试图使用 query_embedding 参数执行一个RPC调用，该参数应为具有特定维度的向量。错误信息表明，函数期望向量维度为4096,但由 Embeddings 示例生成的向量维度为1536。
要解决此问题，你需要确保由 Embeddings 示例生成的向量与预期的维度相匹配。这可能包括：

  1. 检查 Embeddings 示例的配置，以确保其设置为生成正确大小(在这种情况下为4096)的向量。
  2. 如果 Embeddings 示例是正确的且无法更改，您可能需要调整 find_brain_closest_query 函数以接受大小为1536的向量。
  3. 或者，如果 find_brain_closest_query 函数无法更改，您可能需要找到一种将1536维向量转换或适应到预期的4096维格式的方法，尽管这可能会导致信息或准确性的损失。
    不幸的是，由于缺乏关于 Embeddings 类在 CustomSupabaseVectorStore 中的具体实现的更多信息，很难提供更具体的解决方案。如果您能提供更多关于此的详细信息，将有助于诊断和解决问题。

来源

关于 Dosu

此响应旨在帮助您节省时间并提高效率。它不是精确解决方案,而是您自己研究的起点。
请帮助我变得更有用！如果这有帮助，请留下一个👍，如果无关紧要，请留下一个👎。
如果你想继续对话，请以 @dosu-bot 开头回复。

赞(0）分享  回复(0）举报  2个月前
ruarlubt

ruarlubt2#

对不起，数据库的种子设置使得它只接受OpenAI。
你能在localhost:54323上删除brain_vectors表中的所有行吗？然后再尝试一次这个过程？

赞(0）分享  回复(0）举报  2个月前
3npbholx

3npbholx3#

想要修复这个bug...。

赞(0）分享  回复(0）举报  2个月前
jgzswidk

jgzswidk4#

请继续：)

在2024年3月17日星期日晚上10点42分11秒，Mirza Ismail Baig <***@***.***> 写道：想要修复这个bug。——直接回复此电子邮件，查看GitHub上的内容(#2356(评论)),或者取消订阅(https://github.com/notifications/unsubscribe-auth/AEVUW3B7QR2XPQFQNFNFHV3YYZ5DHAVCNFSM6AAAAABE2BK4ISVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMBSHE3TEMJSHE)。您收到此邮件是因为您进行了评论。消息ID:QuivrHQ/quivr/issues/2356/2002972129@github.com

赞(0）分享  回复(0）举报  2个月前
c8ib6hqw

c8ib6hqw5#

添加一个大脑，但即使brains_vector表为空，仍然出现错误。

赞(0）分享  回复(0）举报  2个月前
biswetbf

biswetbf6#

在这里，您可以找到关于模式调整的评论。修复模型属性#2690

赞(0）分享  回复(0）举报  2个月前
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备2022004421号-2 NULL123 https://www.null123.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com