Create a new turn in the chat

POST 
https://api.vectara.io/v2/chats/:chat_id/turns

Create a new turn in the chat. Each conversation has a series of turn objects, which are the sequence of message and response pairs that make up the dialog.

Request

Path Parameters

chat_id stringrequired

Possible values: Value must match regular expression cht_.+$

The ID of the chat.

Header Parameters

Request-Timeout integer

Possible values: >= 1

The API will make a best effort to complete the request in the specified seconds or time out.

Request-Timeout-Millis integer

Possible values: >= 1

The API will make a best effort to complete the request in the specified milliseconds or time out.

application/json

Body

querystringrequired
The chat message or question.
Example: How can I use the Vectara platform?
search object
The parameters to search one or more corpora.
corpora object[]required
The corpora that you want to search.
Possible values: >= 1
Array [
custom_dimensions object
The custom dimensions as additional weights.
property name*double
metadata_filterstring
The filter string used to narrow the search based on metadata attributes. The query against this corpus will be confined to document parts that match the metadata_filter. Only metadata fields set as filter_attributes on the corpus can be filtered. Filter syntax is similar to a SQL WHERE clause. See metadata filters documentation for more information.
Example: doc.title = 'Charlotte''s Web'
lexical_interpolationfloat
How much to weigh lexical scores compared to the embedding score. 0 means lexical search is not used at all, and 1 means only lexical search is used.
Possible values: >= 0 and <= 1
Example: 0.025
semanticsSearchSemantics (string)
Indicates whether to consider a query against this corpus as a query or a response.
Possible values: [default, query, response]
Default value: default
corpus_keyCorpusKey (string)required
A user-provided key for a corpus.
Possible values: <= 50 characters, Value must match regular expression [a-zA-Z0-9_\=\-]+$
Example: my-corpus
querystring
Query for a particular corpus that will override the overall query if present.
]
offsetint32
Specifies how many results into the result to skip. This is useful for pagination.
Possible values: >= 0
Default value: 0
limitint32
The maximum number of results returned.
Possible values: >= 1
Default value: 10
context_configuration object
Configuration on the presentation of each document part in the result set.
characters_beforeint32
The number of characters that are shown before the matching document part. This is useful to show the context of the document part in the wider document. Ignored if sentences_before is set. Vectara will capture the full sentence that contains the captured characters, to not lose the meaning caused by a truncated word or sentence.
Possible values: >= 0
Default value: 0
Example: 30
characters_afterint32
The number of characters that are shown after the matching document part. This is useful to show the context of the document part in the wider document. Ignored if sentences_after is set. Vectara will capture the full sentence that contains the captured characters, to not lose the meaning caused by a truncated word or sentence.
Possible values: >= 0
Default value: 0
Example: 30
sentences_beforeint32
The number of sentences that are shown before the matching document part. This is useful to show the context of the document part in the wider document.
Possible values: >= 0
Default value: 0
Example: 3
sentences_afterint32
The number of sentences that are shown after the matching document part. This is useful to show the context of the document part in the wider document.
Possible values: >= 0
Default value: 0
Example: 3
start_tagstring
The tag that wraps the document part at the start. This is often used to provide a start HTML/XML tag or some other delimiter you can use in an application to understand where to provide highlighting in your UI and understand where the context before ends and the document part begins.
Example: <em>
end_tagstring
The tag that wraps the document part at the end. This is often used to provide a start HTML/XML tag or some other delimiter you can use in an application to understand where to provide highlighting in your UI and understand where the context before ends and the document part begins.
Example: </em>
reranker object
Rerank results of the search. Rerankers are very powerful tools to improve the order of search results. By default the search will use the most powerful reranker available to the customer's plan. To disable reranking, set the reranker type to "none".
type
Rerank results of the search. Rerankers are very powerful tools to improve the order of search results. By default the search will use the most powerful reranker available to the customer's plan. To disable reranking, set the reranker type to "none".
Possible values: [customer_reranker, userfn, mmr, chain, none]
customer_reranker
reranker_idstringdeprecated
The ID of the reranker. The multilingual reranker that may be specified is rnk_272725719. Do not specify the MMR reranker ID here, and instead, use the MMR reranker object type. Deprecated: Use reranker_name instead.
Possible values: Value must match regular expression rnk_(?!272725718)\d+
Example: rnk_272725719
reranker_namestring
The name of the reranker. Do not specify the MMR reranker name here. Instead, use the MMR reranker object type.
Example: Rerank_Multilingual_v1
limitint32
Specifies the maximum number of results to be returned after the reranking process. When a reranker is applied, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Sorts the reranked results based on their new scores.
3. Returns the top N results, where N is the value specified by this limit.
Note: This limit is applied per reranking stage. In a chain of rerankers, each reranker can have its own limit, potentially reducing the number of results at each stage.
Possible values: >= 1
cutofffloat
Specifies the minimum score threshold for results to be included after the reranking process. When a reranker is applied with a cutoff, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Applies the cutoff, removing any results with scores below the specified threshold.
3. Returns the remaining results, sorted by their new scores.
Note: This cutoff is applied per reranking stage. In a chain of rerankers, each reranker can have its own cutoff, potentially further reducing the number of results at each stage. If both 'limit' and 'cutoff' are specified, the cutoff is applied first, followed by the limit.
userfn
user_functionstring
The user defined function.
Example: get('$.score') * get('$.document_metadata.boost')
limitint32
Specifies the maximum number of results to be returned after the reranking process. When a reranker is applied, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Sorts the reranked results based on their new scores.
3. Returns the top N results, where N is the value specified by this limit.
Note: This limit is applied per reranking stage. In a chain of rerankers, each reranker can have its own limit, potentially reducing the number of results at each stage.
Possible values: >= 1
cutofffloat
Specifies the minimum score threshold for results to be included after the reranking process. When a reranker is applied with a cutoff, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Applies the cutoff, removing any results with scores below the specified threshold.
3. Returns the remaining results, sorted by their new scores.
Note: This cutoff is applied per reranking stage. In a chain of rerankers, each reranker can have its own cutoff, potentially further reducing the number of results at each stage. If both 'limit' and 'cutoff' are specified, the cutoff is applied first, followed by the limit.
mmr
diversity_biasfloat
The diversity bias. Higher values indicate more diversity.
Example: 0.3
limitint32
Specifies the maximum number of results to be returned after the reranking process. When a reranker is applied, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Sorts the reranked results based on their new scores.
3. Returns the top N results, where N is the value specified by this limit.
Note: This limit is applied per reranking stage. In a chain of rerankers, each reranker can have its own limit, potentially reducing the number of results at each stage.
Possible values: >= 1
cutofffloat
Specifies the minimum score threshold for results to be included after the reranking process. When a reranker is applied with a cutoff, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Applies the cutoff, removing any results with scores below the specified threshold.
3. Returns the remaining results, sorted by their new scores.
Note: This cutoff is applied per reranking stage. In a chain of rerankers, each reranker can have its own cutoff, potentially further reducing the number of results at each stage. If both 'limit' and 'cutoff' are specified, the cutoff is applied first, followed by the limit.
chain
rerankersundefined[]required
Specify an array of rerankers to apply to search results consecutively.
Possible values: <= 50
none
limitint32
Specifies the maximum number of results to be returned after the reranking process. When a reranker is applied, it performs the following steps:
1. Reranks all input results according to its algorithm.
2. Sorts the reranked results based on their new scores.
3. Returns the top N results, where N is the value specified by this limit.
Note: This limit is applied per reranking stage. In a chain of rerankers, each reranker can have its own limit, potentially reducing the number of results at each stage.
Possible values: >= 1
generation object
The parameters to control generation.
generation_preset_namestring
The preset values to use to feed the query results and other context to the model.
A generation_preset is an object with a bundle of properties that specifies:
• The prompt_template that is rendered and then sent to the LLM.
• The LLM used.
• model_parameters such as temperature.
All of these properties except the model can be overridden by setting them in this object. Even when a prompt_template is set, the generation_preset_name is used to set the model used. See model_parameters.model if you want to set the model explicitly.
If generation_preset_name is not set, the Vectara platform will use the default model and prompt.
Possible values: non-empty
Example: vectara-summary-ext-v1.2.0
prompt_namestringdeprecated
Use generation_preset_name instead of prompt_name.
Possible values: non-empty
Example: vectara-summary-ext-v1.2.0
max_used_search_resultsint32
The maximum number of search results to be available to the prompt.
Possible values: >= 0
Default value: 5
prompt_templatestring
Vectara manages both system and user roles and prompts for the generative LLM out of the box by default. However, users can override the prompt_template via this variable. The prompt_template is in the form of an Apache Velocity template. For more details on how to configure the prompt_template, see the long-form documentation.
Example: [ {"role": "system", "content": "You are a helpful search assistant."}, #foreach ($qResult in $vectaraQueryResults) {"role": "user", "content": "Given the $vectaraIdxWord[$foreach.index] search result."}, {"role": "assistant", "content": "${qResult.getText()}" }, #end {"role": "user", "content": "Generate a summary for the query '${vectaraQuery}' based on the above results."} ]
prompt_textstringdeprecated
This property is deprecated in favor of clearer naming. Use prompt_template. This property will be ignored if prompt_template is set.
Example: [ {"role": "system", "content": "You are a helpful search assistant."}, #foreach ($qResult in $vectaraQueryResults) {"role": "user", "content": "Given the $vectaraIdxWord[$foreach.index] search result."}, {"role": "assistant", "content": "${qResult.getText()}" }, #end {"role": "user", "content": "Generate a summary for the query '${vectaraQuery}' based on the above results."} ]
max_response_charactersint32
Controls the length of the generated output. This is a rough estimate and not a hard limit: the end output can be longer or shorter than this value. This is generally implemented by including the max_response_characters in the prompt, and the LLM's instruction following capability dictates how closely the generated output is limited.
Possible values: >= 0
Example: 300
response_languageLanguage (string)
Languages that the Vectara platform supports.
Possible values: [auto, eng, deu, fra, zho, kor, ara, rus, tha, nld, ita, por, spa, jpn, pol, tur, vie, ind, ces, ukr, ell, heb, fas, hin, urd, swe, ben, msa, ron]
Default value: auto
model_parameters object
The parameters for the model. WARNING: This is an experimental feature, and breakable at any point with virtually no notice. It is meant for experimentation to converge on optimal parameters that can then be set in the prompt definitions.
llm_namestring
The model (e.g., gpt-4) to use for summarization. If specified, it will override the model behind generation_preset_name.
Example: gpt4
max_tokensint32
The maximum number of tokens to be returned by the model.
Possible values: >= 1
temperaturefloat
The sampling temperature to use. Higher values make the output more random, while lower values make it more focused and deterministic.
frequency_penaltyfloat
Higher values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
presence_penaltyfloat
Higher values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
citations object
Style the generator should use when making citations.
stylestring
The citation style to be used in summary. Can be one of:
• numeric - Citations formatted as simple numerals: [1], [2] ...
• none - Citations removed from text.
• html - Citation formatted as a URL like <a href="url_pattern">text_pattern</a>.
• markdown - Formatted as [text_pattern](url_pattern).
Possible values: [none, numeric, html, markdown]
url_patternstring
The URL pattern if the citation_style is set to html or markdown. The pattern can access metadata attributes in the document or part. e.g. https://my.doc/foo/{doc.id}/{part.id}
The default url_pattern is an empty string.
Example: https://vectara.com/documents/{doc.id}
text_patternstring
The text pattern if the citation_style is set to html or markdown. This pattern sets the href for HTML or the text within [] in markdown, and defaults to N being the index of result if it is not set.
The default citation style looks like [N](<url_pattern>) for markdown.
You can use metadata attributes in the text_pattern. For example, the pattern {doc.title} with citation style markdown would result in final citation output like [Title](<url_pattern>) when the document's metadata includes {"title":"Title"}.
Example: {doc.title}
enable_factual_consistency_scoreboolean
Enable returning the factual consistency score with query results.
Default value: true
chat object
Parameters to control chat behavior.
storeboolean
Indicates whether to store chat messages and response messages.
Default value: true
save_historyboolean
Indicates whether to save the chat in both the chat and query history. This overrides chat.store.
Default value: true
intelligent_query_rewritingboolean
Indicates whether to enable intelligent query rewriting. When enabled, the platform will attempt to extract metadata filter and rewrite the query to improve search results.
Default value: false
stream_responseboolean
Indicates whether the response should be streamed or not.
Default value: false

Responses

200

A response to a chat request.

application/json

Schema

Schema

chat_idstring
If the chat response was stored, the ID of the chat.
turn_idstring
If the chat response was stored, the ID of the turn.
answerstring
The message from the chat model for the chat message.
response_languageLanguage (string)
Languages that the Vectara platform supports.
Possible values: [auto, eng, deu, fra, zho, kor, ara, rus, tha, nld, ita, por, spa, jpn, pol, tur, vie, ind, ces, ukr, ell, heb, fas, hin, urd, swe, ben, msa, ron]
Default value: auto
search_results object[]
The ranked search results that the chat model used.
Array [
textstring
The document part altered by the context configuration that matches the query.
scoredouble
The score of the individual result.
part_metadata object
The metadata for the document part.
property name*any
The metadata for the document part.
document_metadata object
The metadata for the document that contains the document part.
property name*any
The metadata for the document that contains the document part.
document_idstring
The ID of the document that contains the document part.
table object
The table that the document part is from.
idstring
The unique ID of the table within the document.
Example: table_1
titlestring
The title of the table.
data object
The data of the table.
headersarray[]
The headers of the table.
rowsarray[]
The rows in the data.
descriptionstring
The description of the table.
request_corpora_indexint32
A query request can search over multiple corpora at a time. This property is set to the index in the list of corpora in the original search request that this search result originated from.
If the query request is only over one corpus, this property is 0.
Possible values: >= 0
Example: 0
]
factual_consistency_scorefloat
Indicates the probability that the summary is factually consistent with the results. The system excludes this property if it encounters excessively large outputs or search results.
rendered_promptstring
The rendered prompt sent to the LLM. Useful when creating customer prompt_template templates.
warningsQueryWarning (string)[]
Non-fatal warnings that occurred during request processing
Possible values: [exceeded_max_input_length_fcs, intelligent_query_rewriting_failed]
rephrased_querystring
View the actual query made to backend that was rephrased by the LLM from the input query.
rewritten_queries object[]
The rewritten queries for the corpora that were searched. Only populated when intelligent_query_rewriting is enabled.
Array [
corpus_keystring
The corpus key that the query was made on.
filter_extraction object
The result of query filter extraction.
querystring
The query rephrased from the input query and executed.
metadata_filterstring
The metadata filter extracted from the input query.
]

Example (auto)

{
  "chat_id": "string",
  "turn_id": "string",
  "answer": "string",
  "response_language": "auto",
  "search_results": [
    {
      "text": "string",
      "score": 0,
      "part_metadata": {},
      "document_metadata": {},
      "document_id": "string",
      "table": {
        "id": "table_1",
        "title": "string",
        "data": {
          "headers": [
            [
              {
                "text_value": "string",
                "int_value": 0,
                "float_value": 0,
                "bool_value": true,
                "colspan": 0,
                "rowspan": 0
              }
            ]
          ],
          "rows": [
            [
              {
                "text_value": "string",
                "int_value": 0,
                "float_value": 0,
                "bool_value": true,
                "colspan": 0,
                "rowspan": 0
              }
            ]
          ]
        },
        "description": "string"
      },
      "request_corpora_index": 0
    }
  ],
  "factual_consistency_score": 0,
  "rendered_prompt": "string",
  "warnings": [
    "exceeded_max_input_length_fcs"
  ],
  "rephrased_query": "string",
  "rewritten_queries": [
    {
      "corpus_key": "string",
      "filter_extraction": {
        "query": "string",
        "metadata_filter": "string"
      }
    }
  ]
}

text/event-stream

Schema

Schema

type

An individual event when the response is streamed.

Possible values: [search_results, chat_info, generation_chunk, generation_end, generation_info, factual_consistency_score, end, error]

search_results

search_results object[]

The ranked search results.

Array [

textstring

The document part altered by the context configuration that matches the query.

scoredouble

The score of the individual result.

part_metadata object

The metadata for the document part.

property name*any

The metadata for the document part.

document_metadata object

The metadata for the document that contains the document part.

property name*any

The metadata for the document that contains the document part.

document_idstring

The ID of the document that contains the document part.

table object

The table that the document part is from.

idstring

The unique ID of the table within the document.

Example: table_1

titlestring

The title of the table.

data object

The data of the table.

headersarray[]

The headers of the table.

rowsarray[]

The rows in the data.

descriptionstring

The description of the table.

request_corpora_indexint32

A query request can search over multiple corpora at a time. This property is set to the index in the list of corpora in the original search request that this search result originated from.

If the query request is only over one corpus, this property is 0.

Possible values: >= 0

Example: 0

]

rewritten_queries object[]

The rewritten queries for the corpora that were searched. Only populated when intelligent_query_rewriting is enabled.

Array [

corpus_keystring

The corpus key that the query was made on.

filter_extraction object

The result of query filter extraction.

querystring

The query rephrased from the input query and executed.

metadata_filterstring

The metadata filter extracted from the input query.

]

chat_info

chat_idstring

ID of the chat.

Possible values: Value must match regular expression cht_.+$

turn_idstring

ID of the turn.

Possible values: Value must match regular expression trn_.+$

generation_chunk

generation_chunkstring

Part of the message from the generator. All summary chunks must be appended together in order to get the full summary.

generation_end

object

generation_info

rendered_promptstring

The rendered prompt sent to the LLM. Useful when creating customer prompt_template templates.

rephrased_querystring

View the actual query made to backend that was rephrased by the LLM from the input query.

factual_consistency_score

factual_consistency_scorefloat

The probability that the summary is factually consistent with the results.

end

object

error

messagesstring[]

The error messages.

Example (auto)

{
  "type": "search_results",
  "search_results": [
    {
      "text": "string",
      "score": 0,
      "part_metadata": {},
      "document_metadata": {},
      "document_id": "string",
      "table": {
        "id": "table_1",
        "title": "string",
        "data": {
          "headers": [
            [
              {
                "text_value": "string",
                "int_value": 0,
                "float_value": 0,
                "bool_value": true,
                "colspan": 0,
                "rowspan": 0
              }
            ]
          ],
          "rows": [
            [
              {
                "text_value": "string",
                "int_value": 0,
                "float_value": 0,
                "bool_value": true,
                "colspan": 0,
                "rowspan": 0
              }
            ]
          ]
        },
        "description": "string"
      },
      "request_corpora_index": 0
    }
  ],
  "rewritten_queries": [
    {
      "corpus_key": "string",
      "filter_extraction": {
        "query": "string",
        "metadata_filter": "string"
      }
    }
  ]
}

400

Turn creation request was malformed.

application/json

Schema

Schema

field_errors object

The errors that relate to specific fields in the request.

property name*string

messagesmessage (string)[]

request_idstring

The ID of the request that can be used to help Vectara support debug what went wrong.

Example (auto)

{
  "field_errors": {},
  "messages": [
    "string"
  ],
  "request_id": "string"
}

403

Permissions do not allow creating a turn in the chat.

application/json

Schema

Schema

messagesmessage (string)[]

The messages describing why the error occurred.

request_idstring

The ID of the request that can be used to help Vectara support debug what went wrong.

Example (auto)

{
  "messages": [
    "Internal server error."
  ],
  "request_id": "string"
}

404

Corpus or chat not found.

application/json

Schema

Schema

idstring

The ID cannot be found.

messagesmessage (string)[]

request_idstring

The ID of the request that can be used to help Vectara support debug what went wrong.

Example (auto)

{
  "id": "string",
  "messages": [
    "string"
  ],
  "request_id": "string"
}

Authorization: x-api-key

name: x-api-keytype: apiKeyin: header

• csharp
• curl
• dart
• go
• http
• java
• javascript
• kotlin
• c
• nodejs
• objective-c
• ocaml
• php
• powershell
• python
• r
• ruby
• rust
• shell
• swift

• HTTPCLIENT
• RESTSHARP

var client = new HttpClient();
var request = new HttpRequestMessage(HttpMethod.Post, "https://api.vectara.io/v2/chats/:chat_id/turns");
request.Headers.Add("Accept", "application/json");
request.Headers.Add("x-api-key", "<x-api-key>");
var content = new StringContent("{\n  \"query\": \"How can I use the Vectara platform?\",\n  \"search\": {\n    \"corpora\": [\n      {\n        \"custom_dimensions\": {},\n        \"metadata_filter\": \"doc.title = 'Charlotte''s Web'\",\n        \"lexical_interpolation\": 0.025,\n        \"semantics\": \"default\",\n        \"corpus_key\": \"my-corpus\",\n        \"query\": \"string\"\n      }\n    ],\n    \"offset\": 0,\n    \"limit\": 10,\n    \"context_configuration\": {\n      \"characters_before\": 30,\n      \"characters_after\": 30,\n      \"sentences_before\": 3,\n      \"sentences_after\": 3,\n      \"start_tag\": \"<em>\",\n      \"end_tag\": \"</em>\"\n    },\n    \"reranker\": {\n      \"type\": \"customer_reranker\",\n      \"reranker_name\": \"Rerank_Multilingual_v1\",\n      \"limit\": 0,\n      \"cutoff\": 0\n    }\n  },\n  \"generation\": {\n    \"generation_preset_name\": \"vectara-summary-ext-v1.2.0\",\n    \"max_used_search_results\": 5,\n    \"prompt_template\": \"[\\n  {\\\"role\\\": \\\"system\\\", \\\"content\\\": \\\"You are a helpful search assistant.\\\"},\\n  #foreach ($qResult in $vectaraQueryResults)\\n     {\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Given the $vectaraIdxWord[$foreach.index] search result.\\\"},\\n     {\\\"role\\\": \\\"assistant\\\", \\\"content\\\": \\\"${qResult.getText()}\\\" },\\n  #end\\n  {\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Generate a summary for the query '${vectaraQuery}' based on the above results.\\\"}\\n]\\n\",\n    \"max_response_characters\": 300,\n    \"response_language\": \"auto\",\n    \"model_parameters\": {\n      \"llm_name\": \"gpt4\",\n      \"max_tokens\": 0,\n      \"temperature\": 0,\n      \"frequency_penalty\": 0,\n      \"presence_penalty\": 0\n    },\n    \"citations\": {\n      \"style\": \"none\",\n      \"url_pattern\": \"https://vectara.com/documents/{doc.id}\",\n      \"text_pattern\": \"{doc.title}\"\n    },\n    \"enable_factual_consistency_score\": true\n  },\n  \"chat\": {\n    \"store\": true\n  },\n  \"save_history\": true,\n  \"intelligent_query_rewriting\": false,\n  \"stream_response\": false\n}", null, "application/json");
request.Content = content;
var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
Console.WriteLine(await response.Content.ReadAsStringAsync());

Request Collapse all

Base URL

https://api.vectara.io

Auth

Security Scheme

ApiKeyAuthOAuth2

ApiKeyAuth

Parameters

chat_id — pathrequired

Request-Timeout — header

Request-Timeout-Millis — header

Body

{
  "query": "How can I use the Vectara platform?",
  "search": {
    "corpora": [
      {
        "custom_dimensions": {},
        "metadata_filter": "doc.title = 'Charlotte''s Web'",
        "lexical_interpolation": 0.025,
        "semantics": "default",
        "corpus_key": "my-corpus",
        "query": "string"
      }
    ],
    "offset": 0,
    "limit": 10,
    "context_configuration": {
      "characters_before": 30,
      "characters_after": 30,
      "sentences_before": 3,
      "sentences_after": 3,
      "start_tag": "<em>",
      "end_tag": "</em>"
    },
    "reranker": {
      "type": "customer_reranker",
      "reranker_name": "Rerank_Multilingual_v1",
      "limit": 0,
      "cutoff": 0
    }
  },
  "generation": {
    "generation_preset_name": "vectara-summary-ext-v1.2.0",
    "max_used_search_results": 5,
    "prompt_template": "[\n  {\"role\": \"system\", \"content\": \"You are a helpful search assistant.\"},\n  #foreach ($qResult in $vectaraQueryResults)\n     {\"role\": \"user\", \"content\": \"Given the $vectaraIdxWord[$foreach.index] search result.\"},\n     {\"role\": \"assistant\", \"content\": \"${qResult.getText()}\" },\n  #end\n  {\"role\": \"user\", \"content\": \"Generate a summary for the query '${vectaraQuery}' based on the above results.\"}\n]\n",
    "max_response_characters": 300,
    "response_language": "auto",
    "model_parameters": {
      "llm_name": "gpt4",
      "max_tokens": 0,
      "temperature": 0,
      "frequency_penalty": 0,
      "presence_penalty": 0
    },
    "citations": {
      "style": "none",
      "url_pattern": "https://vectara.com/documents/{doc.id}",
      "text_pattern": "{doc.title}"
    },
    "enable_factual_consistency_score": true
  },
  "chat": {
    "store": true
  },
  "save_history": true,
  "intelligent_query_rewriting": false,
  "stream_response": false
}

ResponseClear

Click the Send API Request button above and see the response here!