Chat Gpt Demo

In this section we have a simple tutorial how to create simple search with 'Quick Start' with ChatGPT integration. Make sure you have access to necessary configs (searchapp, search, config). If you don't have access to this configs please contact an administration to provide it

Create config

Create config

1. Go to Quasiris Search Cloud
2. Enter 'Config' in the top left search input
3. Click on 'Config'
4. Create a config with name 'chat-gpt-integration-config'
5. In tab 'Config' post a json

   {
     "type": "searchResultRefinement",
     "searchResultRefinement": {
        "requestTemplate": "Title is '${(searchResults['chat-gpt-quick-start-demo'].documents[0].document.title)!\"\"}'",
        "appendToSearchContextKey": "biking",
        "contextString": "This is a chat for the application, where I would enter a query, and you would answer the question from this query. Possible answers are only yes, no, unknown. Don't add any comments or symbols. ONLY 'yes', 'no', 'unknown'. \nWe are at biking shop, I want to know if the title user enter somehow connected to biking topic."
     }
   }
6. Click 'Save'

Run Quick Start

1. Go to Quick Start
2. Enter code chat-gpt-quick-start-demo
3. Enter data

[
    {
        "title": "mountain bike",
        "name": "name of the bike",
        "description": "Perfect for sport"
    },
    {
        "title": "kitchen scales",
        "name": "name of the scalse",
        "description": "Perfect for kitchen"
    }
]

4. Click Create Search
5. Click Next until you see Apply button
6. Click Apply
7. Go to Search config
8. Go to your config chat-gpt-quick-start-demo
9. Go to Pipeline tab
10. As Pipeline Type choose Custom
11. Enter yaml document

!!com.quasiris.qsf.pipeline.Pipeline
id: search-pipeline
timeout: 4000
filterList:
  - !!com.quasiris.qsf.pipeline.filter.DebugFilter
    active: true
    id: search-pipeline.DebugFilter
  - !!com.quasiris.qsc.search.service.query.QscSearchQueryFilter
    active: true
    id: search-pipeline.QscSearchQueryFilter
  - !!com.quasiris.qsc.search.service.rules.QueryRuleFilter
    active: true
    baseUrl: {{ searchIndexBaseUrl }}
    env: {{ env }}
    id: queryRuleFilter
  - !!com.quasiris.qsf.pipeline.filter.elastic.ElasticFilter
    active: true
    baseUrl: {{searchIndexBaseUrl}}
    id: searchElasticFilter
    resultSetId: {{searchCode}}
    queryTransformer: !!com.quasiris.qsc.search.service.QscSearchQueryTransformer
      profile: {{profile}}
    searchResultTransformer: !!com.quasiris.qsc.search.service.QscResultTransformer
    elasticSearchClient: !!com.quasiris.qsf.commons.elasticsearch.client.ElasticSearchClient
      useApacheClient: false
  - !!com.quasiris.qsf.pipeline.filter.ConditionFilter
    active: true
    condition: !!com.quasiris.qsf.pipeline.filter.conditions.EmptyResultCondition
      resultSetId: {{searchCode}}
    id: conditional.isSpellcheck
    pipeline:
      filterList:
        - !!com.quasiris.qsf.pipeline.filter.TokenizerFilter
          active: true
          id: qsc-spellcheck.TokenizerFilter
        - !!com.quasiris.qsf.pipeline.filter.elastic.SpellCheckElasticFilter
          active: true
          baseUrl: {{searchIndexBaseUrl}}-spellcheck
          id: qsc-spellcheck.SpellCheckElasticFilter
          maxTokenLenght: 10
          minTokenLenght: 4
          minTokenWeight: 1
          sentenceScoringEnabled: false
          restartPipelineId: search-pipeline
      id: qsc-spellcheck
      timeout: 1000
  - !!com.quasiris.qsf.pipeline.filter.QSFQLResponseRefinementFilter
    active: true
    id: search-pipeline.QSFQLResponseRefinementFilter
    resultId: {{searchCode}}
  - !!com.quasiris.qsc.chatgpt.filter.ChatGPTFilter
    active: true
    apiKey: "chat-gpt-api-key"
    modelId: "gpt-3.5-turbo"
    chatGptConfigCode: "chat-gpt-integration-config"
    resultSetId: {{searchCode}}
    maxTokens: 10
    timeoutMills: 8000
    temperature: 0
  - !!com.quasiris.qsf.pipeline.filter.elastic.ElasticTrackingFilter
    active: true
    baseUrl: {{trackingIndexBaseUrl}}
    customParameter:
      app: search
      searchCode: {{searchCode}}
      tenantCode: {{tenant}}
      env: {{env}}
    id: search-pipeline.ElasticTrackingFilter
    idFieldName: id
    resultSetId: {{searchCode}}
    rotation: none
    trackingId: null

12. Set the right api key in yaml
13. Save the config

Test the search

The search configuration now is configured to check if the title of the first document is about biking. It must return 'yes' if it is, and 'no' if it is not. If chat gpt doesn't know it must answer 'unknown'.

1. Go to your search config
2. Go to api
3. Check context field. See the result
4. Change q=kitchen query parameter. ChatGPT must answer 'no'
5. Change q=bike query parameter. ChatGPT must answer 'yes'
6. Change q=abdgdfgbdfg query parameter. ChatGPT must answer 'unknown', because we have empty document list for this query