# Question answering The Semantic Retrieval API provides a hosted question answering service for building Retrieval Augmented Generation (RAG) systems using Google's infrastructure. ## Method: models.generateAnswer - [Endpoint](https://ai.google.dev/api/semantic-retrieval/question-answering#body.HTTP_TEMPLATE) - [Path parameters](https://ai.google.dev/api/semantic-retrieval/question-answering#body.PATH_PARAMETERS) - [Request body](https://ai.google.dev/api/semantic-retrieval/question-answering#body.request_body) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#body.request_body.SCHEMA_REPRESENTATION) - [Response body](https://ai.google.dev/api/semantic-retrieval/question-answering#body.response_body) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#body.GenerateAnswerResponse.SCHEMA_REPRESENTATION) - [Authorization scopes](https://ai.google.dev/api/semantic-retrieval/question-answering#body.aspect) - [GroundingPassages](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassages) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassages.SCHEMA_REPRESENTATION) - [GroundingPassage](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassage) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassage.SCHEMA_REPRESENTATION) - [SemanticRetrieverConfig](https://ai.google.dev/api/semantic-retrieval/question-answering#SemanticRetrieverConfig) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#SemanticRetrieverConfig.SCHEMA_REPRESENTATION) - [AnswerStyle](https://ai.google.dev/api/semantic-retrieval/question-answering#AnswerStyle) - [InputFeedback](https://ai.google.dev/api/semantic-retrieval/question-answering#InputFeedback) - [JSON representation](https://ai.google.dev/api/semantic-retrieval/question-answering#InputFeedback.SCHEMA_REPRESENTATION) - [BlockReason](https://ai.google.dev/api/semantic-retrieval/question-answering#BlockReason) Generates a grounded answer from the model given an input `GenerateAnswerRequest`. ### Endpoint post `https:``/``/generativelanguage.googleapis.com``/v1beta``/{model=models``/*}:generateAnswer` ### Path parameters `model` `string` Required. The name of the `Model` to use for generating the grounded response. Format: `model=models/{model}`. It takes the form `models/{model}`. ### Request body The request body contains data with the following structure: Fields `contents[]` `object (`[Content](https://ai.google.dev/api/caching#Content)`)` Required. The content of the current conversation with the `Model`. For single-turn queries, this is a single question to answer. For multi-turn queries, this is a repeated field that contains conversation history and the last `Content` in the list containing the question. Note: `models.generateAnswer` only supports queries in English. `answerStyle` `enum (`[AnswerStyle](https://ai.google.dev/api/semantic-retrieval/question-answering#AnswerStyle)`)` Required. Style in which answers should be returned. `safetySettings[]` `object (`[SafetySetting](https://ai.google.dev/api/generate-content#v1beta.SafetySetting)`)` Optional. A list of unique `SafetySetting` instances for blocking unsafe content. This will be enforced on the `GenerateAnswerRequest.contents` and `GenerateAnswerResponse.candidate`. There should not be more than one setting for each `SafetyCategory` type. The API will block any contents and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each `SafetyCategory` specified in the safetySettings. If there is no `SafetySetting` for a given `SafetyCategory` provided in the list, the API will use the default safety setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_HARASSMENT are supported. Refer to the [guide](https://ai.google.dev/gemini-api/docs/safety-settings) for detailed information on available safety settings. Also refer to the [Safety guidance](https://ai.google.dev/gemini-api/docs/safety-guidance) to learn how to incorporate safety considerations in your AI applications. `grounding_source` `Union type` The sources in which to ground the answer. `grounding_source` can be only one of the following: `inlinePassages` `object (`[GroundingPassages](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassages)`)` Passages provided inline with the request. `semanticRetriever` `object (`[SemanticRetrieverConfig](https://ai.google.dev/api/semantic-retrieval/question-answering#SemanticRetrieverConfig)`)` Content retrieved from resources created via the Semantic Retriever API. `temperature` `number` Optional. Controls the randomness of the output. Values can range from \[0.0,1.0\], inclusive. A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model. A low temperature (\~0.2) is usually recommended for Attributed-Question-Answering use cases. ### Response body Response from the model for a grounded answer. If successful, the response body contains data with the following structure: Fields `answer` `object (`[Candidate](https://ai.google.dev/api/generate-content#v1beta.Candidate)`)` Candidate answer from the model. Note: The model *always* attempts to provide a grounded answer, even when the answer is unlikely to be answerable from the given passages. In that case, a low-quality or ungrounded answer may be provided, along with a low `answerableProbability`. `answerableProbability` `number` Output only. The model's estimate of the probability that its answer is correct and grounded in the input passages. A low `answerableProbability` indicates that the answer might not be grounded in the sources. When `answerableProbability` is low, you may want to: - Display a message to the effect of "We couldn't answer that question" to the user. - Fall back to a general-purpose LLM that answers the question from world knowledge. The threshold and nature of such fallbacks will depend on individual use cases. `0.5` is a good starting threshold. `inputFeedback` `object (`[InputFeedback](https://ai.google.dev/api/semantic-retrieval/question-answering#InputFeedback)`)` Output only. Feedback related to the input data used to answer the question, as opposed to the model-generated response to the question. The input data can be one or more of the following: - Question specified by the last entry in `GenerateAnswerRequest.content` - Conversation history specified by the other entries in `GenerateAnswerRequest.content` - Grounding sources (`GenerateAnswerRequest.semantic_retriever` or `GenerateAnswerRequest.inline_passages`) | JSON representation | |----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | ``` { "answer": { object (https://ai.google.dev/api/generate-content#v1beta.Candidate) }, "answerableProbability": number, "inputFeedback": { object (https://ai.google.dev/api/semantic-retrieval/question-answering#InputFeedback) } } ``` | ## GroundingPassages A repeated list of passages. Fields `passages[]` `object (`[GroundingPassage](https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassage)`)` List of passages. | JSON representation | |---------------------------------------------------------------------------------------------------------------------------| | ``` { "passages": [ { object (https://ai.google.dev/api/semantic-retrieval/question-answering#GroundingPassage) } ] } ``` | ## GroundingPassage Passage included inline with a grounding configuration. Fields `id` `string` Identifier for the passage for attributing this passage in grounded answers. `content` `object (`[Content](https://ai.google.dev/api/caching#Content)`)` Content of the passage. | JSON representation | |---------------------------------------------------------------------------------------------| | ``` { "id": string, "content": { object (https://ai.google.dev/api/caching#Content) } } ``` | ## SemanticRetrieverConfig Configuration for retrieving grounding content from a `Corpus` or `Document` created using the Semantic Retriever API. Fields `source` `string` Required. Name of the resource for retrieval. Example: `corpora/123` or `corpora/123/documents/abc`. `query` `object (`[Content](https://ai.google.dev/api/caching#Content)`)` Required. Query to use for matching `Chunk`s in the given resource by similarity. `metadataFilters[]` `object (`[MetadataFilter](https://ai.google.dev/api/semantic-retrieval/corpora#v1beta.MetadataFilter)`)` Optional. Filters for selecting `Document`s and/or `Chunk`s from the resource. `maxChunksCount` `integer` Optional. Maximum number of relevant `Chunk`s to retrieve. `minimumRelevanceScore` `number` Optional. Minimum relevance score for retrieved relevant `Chunk`s. | JSON representation | |---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | ``` { "source": string, "query": { object (https://ai.google.dev/api/caching#Content) }, "metadataFilters": [ { object (https://ai.google.dev/api/semantic-retrieval/corpora#v1beta.MetadataFilter) } ], "maxChunksCount": integer, "minimumRelevanceScore": number } ``` | ## AnswerStyle Style for grounded answers. | Enums || |----------------------------|--------------------------------------------------------------------------------------------------------------------------------------------| | `ANSWER_STYLE_UNSPECIFIED` | Unspecified answer style. | | `ABSTRACTIVE` | Succinct but abstract style. | | `EXTRACTIVE` | Very brief and extractive style. | | `VERBOSE` | Verbose style including extra details. The response may be formatted as a sentence, paragraph, multiple paragraphs, or bullet points, etc. | ## InputFeedback Feedback related to the input data used to answer the question, as opposed to the model-generated response to the question. Fields `safetyRatings[]` `object (`[SafetyRating](https://ai.google.dev/api/generate-content#v1beta.SafetyRating)`)` Ratings for safety of the input. There is at most one rating per category. `blockReason` `enum (`[BlockReason](https://ai.google.dev/api/semantic-retrieval/question-answering#BlockReason)`)` Optional. If set, the input was blocked and no candidates are returned. Rephrase the input. | JSON representation | |-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | ``` { "safetyRatings": [ { object (https://ai.google.dev/api/generate-content#v1beta.SafetyRating) } ], "blockReason": enum (https://ai.google.dev/api/semantic-retrieval/question-answering#BlockReason) } ``` | ## BlockReason Specifies what was the reason why input was blocked. | Enums || |----------------------------|------------------------------------------------------------------------------------------------------------------| | `BLOCK_REASON_UNSPECIFIED` | Default value. This value is unused. | | `SAFETY` | Input was blocked due to safety reasons. Inspect `safetyRatings` to understand which safety category blocked it. | | `OTHER` | Input was blocked due to other reasons. |