postgresql postgres函数返回运算符不存在(pg_vector)

rjee0c15  于 2023-04-11  发布在  PostgreSQL
关注(0)|答案(1)|浏览(283)

详细的GitHub问题在这里打开https://github.com/supabase/supabase/issues/13337
我之所以在这里提出另一个问题,是想寻求更有经验的人来帮助。
我有一个Postgres函数来查找前10个最相关的向量。我从一个supabase无服务器函数调用了这个函数,但日志返回500。
我遇到的错误与运算符<#>有关。似乎PostgreSQL无法为pgvector扩展提供的vector类型找到此运算符。

详细日志消息

Failed to match page sections: {"code":"42883","details":null,"hint":"No operator matches the given name and argument types. You might need to add explicit type casts.","message":"operator does not exist: extensions.vector <=> extensions.vector"}

Postgres函数

create or replace function match_page_sections(embedding vector(1536), match_threshold float, match_count int, min_content_length int)
returns table (id bigint, page_id bigint, slug text, heading text, content text, similarity float)
language plpgsql
as $$
#variable_conflict use_variable
begin
  return query
  select
    page_section.id,
    page_section.page_id,
    page_section.slug,
    page_section.heading,
    page_section.content,
    (page_section.embedding <#> embedding) * -1 as similarity
  from page_section

  -- We only care about sections that have a useful amount of content
  where length(page_section.content) >= min_content_length

  -- The dot product is negative because of a Postgres limitation, so we negate it
  and (page_section.embedding <#> embedding) * -1 > match_threshold

  -- OpenAI embeddings are normalized to length 1, so
  -- cosine similarity and dot product will produce the same results.
  -- Using dot product which can be computed slightly faster.
  --
  -- For the different syntaxes, see https://github.com/pgvector/pgvector
  order by page_section.embedding <#> embedding
  
  limit match_count;
end;
$$;

无服务器函数(发生在第108行)

import { serve } from 'https://deno.land/std@0.170.0/http/server.ts'
import 'https://deno.land/x/xhr@0.2.1/mod.ts'
import { createClient } from 'https://esm.sh/@supabase/supabase-js@2.5.0'
import { codeBlock, oneLine } from 'https://esm.sh/common-tags@1.8.2'
import GPT3Tokenizer from 'https://esm.sh/gpt3-tokenizer@1.1.5'
import {
  ChatCompletionRequestMessage,
  ChatCompletionRequestMessageRoleEnum,
  Configuration,
  CreateChatCompletionRequest,
  OpenAIApi,
} from 'https://esm.sh/openai@3.2.1'

class ApplicationError extends Error {
  constructor(message: string, public data: Record<string, any> = {}) {
    super(message)
  }
}

class UserError extends ApplicationError {}

const openAiKey = Deno.env.get('OPENAI_KEY')
const supabaseUrl = Deno.env.get('SUPABASE_URL')
const supabaseServiceKey = Deno.env.get('SUPABASE_SERVICE_ROLE_KEY')

export const corsHeaders = {
  'Access-Control-Allow-Origin': '*',
  'Access-Control-Allow-Headers': 'authorization, x-client-info, apikey, content-type',
}

serve(async (req) => {
  try {
    // Handle CORS
    if (req.method === 'OPTIONS') {
      return new Response('ok', { headers: corsHeaders })
    }

    if (!openAiKey) {
      throw new ApplicationError('Missing environment variable OPENAI_KEY')
    }

    if (!supabaseUrl) {
      throw new ApplicationError('Missing environment variable SUPABASE_URL')
    }

    if (!supabaseServiceKey) {
      throw new ApplicationError('Missing environment variable SUPABASE_SERVICE_ROLE_KEY')
    }

    const requestData = await req.json()

    if (!requestData) {
      throw new UserError('Missing request data')
    }

    const { query } = requestData

    if (!query) {
      throw new UserError('Missing query in request data')
    }

    // Intentionally log the query
    console.log({ query })

    const sanitizedQuery = query.trim()

    const supabaseClient = createClient(supabaseUrl, supabaseServiceKey)

    const configuration = new Configuration({ apiKey: openAiKey })
    const openai = new OpenAIApi(configuration)

    // Moderate the content to comply with OpenAI T&C
    const moderationResponse = await openai.createModeration({ input: sanitizedQuery })

    const [results] = moderationResponse.data.results

    if (results.flagged) {
      throw new UserError('Flagged content', {
        flagged: true,
        categories: results.categories,
      })
    }

    const embeddingResponse = await openai.createEmbedding({
      model: 'text-embedding-ada-002',
      input: sanitizedQuery.replaceAll('\n', ' '),
    })

    if (embeddingResponse.status !== 200) {
      throw new ApplicationError('Failed to create embedding for question', embeddingResponse)
    }

    const [{ embedding }] = embeddingResponse.data.data

    console.log({ embedding })

    const { error: matchError, data: pageSections } = await supabaseClient.rpc(
      'match_page_sections',
      {
        embedding,
        match_threshold: 0.78,
        match_count: 10,
        min_content_length: 50,
      }
    )

    if (matchError) {
      throw new ApplicationError('Failed to match page sections', matchError)
    }

    const tokenizer = new GPT3Tokenizer({ type: 'gpt3' })
    let tokenCount = 0
    let contextText = ''

    for (let i = 0; i < pageSections.length; i++) {
      const pageSection = pageSections[i]
      const content = pageSection.content
      const encoded = tokenizer.encode(content)
      tokenCount += encoded.text.length

      if (tokenCount >= 1500) {
        break
      }

      contextText += `${content.trim()}\n---\n`
    }

    const prompt = codeBlock`
      ${oneLine`
        You are a very enthusiastic Chatti representative who loves
        to help people! Given the following sections from the Chatti
        documentation, answer the question using only that information,
        outputted in markdown format. If you are unsure and the answer
        is not explicitly written in the documentation, say
        "Sorry, I don't know how to help with that."
      `}

      Context sections:
      ${contextText}

      Question: """
      ${sanitizedQuery}
      """

      Answer as markdown (including related code snippets if available):
    `

    const messages: ChatCompletionRequestMessage[] = [
      {
        role: ChatCompletionRequestMessageRoleEnum.System,
        content: codeBlock`
          ${oneLine`
            You are a very enthusiastic Chatti AI who loves
            to help people! Given the following information from
            the Supabase documentation, answer the user's question using
            only that information, outputted in markdown format.
          `}

          ${oneLine`
            If you are unsure
            and the answer is not explicitly written in the documentation, say
            "Sorry, I don't know how to help with that."
          `}
          
          ${oneLine`
            Always include related code snippets if available.
          `}
        `,
      },
      {
        role: ChatCompletionRequestMessageRoleEnum.User,
        content: codeBlock`
          Here is the Chati documentation:
          ${contextText}
        `,
      },
      {
        role: ChatCompletionRequestMessageRoleEnum.User,
        content: codeBlock`
          ${oneLine`
            Answer my next question using only the above documentation.
            You must also follow the below rules when answering:
          `}
          ${oneLine`
            - Do not make up answers that are not provided in the documentation.
          `}
          ${oneLine`
            - If you are unsure and the answer is not explicitly written
            in the documentation context, say
            "Sorry, I don't know how to help with that."
          `}
          ${oneLine`
            - Prefer splitting your response into multiple paragraphs.
          `}
          ${oneLine`
            - Output as markdown with code snippets if available.
          `}
        `,
      },
      {
        role: ChatCompletionRequestMessageRoleEnum.User,
        content: codeBlock`
          Here is my question:
          ${oneLine`${sanitizedQuery}`}
      `,
      },
    ]

    const completionOptions: CreateChatCompletionRequest = {
      model: 'gpt-3.5-turbo',
      messages,
      max_tokens: 1024,
      temperature: 0,
      stream: true,
    }

    const response = await fetch('https://api.openai.com/v1/chat/completions', {
      headers: {
        Authorization: `Bearer ${openAiKey}`,
        'Content-Type': 'application/json',
      },
      method: 'POST',
      body: JSON.stringify(completionOptions),
    })

    if (!response.ok) {
      const error = await response.json()
      throw new ApplicationError('Failed to generate completion', error)
    }

    // Proxy the streamed SSE response from OpenAI
    return new Response(response.body, {
      headers: {
        ...corsHeaders,
        'Content-Type': 'text/event-stream',
      },
    })
  } catch (err: unknown) {
    if (err instanceof UserError) {
      return new Response(
        JSON.stringify({
          error: err.message,
          data: err.data,
        }),
        {
          status: 400,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' },
        }
      )
    } else if (err instanceof ApplicationError) {
      // Print out application errors with their additional data
      console.error(`${err.message}: ${JSON.stringify(err.data)}`)
    } else {
      // Print out unexpected errors as is to help with debugging
      console.error(err)
    }

    // TODO: include more response info in debug environments
    return new Response(
      JSON.stringify({
        error: 'There was an error processing your request',
      }),
      {
        status: 500,
        headers: { ...corsHeaders, 'Content-Type': 'application/json' },
      }
    )
  }
})
ibrsph3r

ibrsph3r1#

我终于找到了问题所在;你必须在扩展模式上安装pg_vector。
如果您正在跟踪https://github.com/supabase/supabase/blob/master/supabase/migrations/20230126220613_doc_embeddings.sql。很可能您不会得到它的工作出于某种原因。
只需手动启用数据库选项卡中的扩展。

相关问题