SMsmartly
Assistants

Create an assistant

Create an assistant

post/generative_ai

Request

Request body

namestring
assistant_typestring
is_archivedboolean
is_sharedboolean
collaboratorsstring[]
typestring

Example request

{
  "name": "My assistant",
  "assistant_type": "rag",
  "query_condensation": {
    "instructions_choice": "both",
    "messages_to_condensate": 20
  },
  "query_expansion": {
    "instructions_choice": "both",
    "messages_to_generate": 3
  },
  "reranking": {
    "algorithm": "cohere-ai-cross-encoder"
  },
  "answer_generation": {
    "instructions_choice": "semantic",
    "maximum_answer_length": 100
  },
  "post_processing": {
    "is_activated": true
  },
  "answer_formatting": {
    "waiting_messages_for_answer_generation": "Génération... \nSynthèse... \nRéponse... \nUn petit moment svp...",
    "waiting_messages_for_search": "Recherche... \nRecherche en cours... \nJ'interroge mon contexte... \nRecherche dans ma base de données... \nJe consulte mes ressources...",
    "waiting_messages_for_analysis": "Analyse... \nAnalyse de votre requête... \nTraitement votre requête... \nTraitement du message... \nAnalyse de votre demande... \nAnalyse en cours... \nTraitement de votre demande... \nCompréhension du message... \nInterprétation en cours... \nÉvaluation de la requête..."
  },
  "source": {
    "sources": [
      {
        "name": "string up",
        "_id": "66716edc649a8d158495d425"
      }
    ]
  },
  "search": {
    "strategy": "semantic",
    "similarity_threshold": 0.79,
    "number_best_results_llm_context": 4,
    "search_results_per_query": 10
  },
  "LLM": {
    "model_id": "66425829914fbb87228da576",
    "model_name": "gpt 4 o",
    "reuse_these_models": true
  },
  "type": "chat"
}

Response

successful

_idstring
namestring
assistant_typestring
is_archivedboolean
is_sharedboolean
user_idstring
collaboratorsstring[]
typestring
createdAtstring date-time
updatedAtstring date-time
__vinteger

Example response

{
  "name": "My assistant",
  "assistant_type": "rag",
  "query_condensation": {
    "instructions_choice": "both",
    "messages_to_condensate": 20
  },
  "query_expansion": {
    "instructions_choice": "both",
    "messages_to_generate": 3
  },
  "reranking": {
    "algorithm": "cohere-ai-cross-encoder"
  },
  "answer_generation": {
    "instructions_choice": "semantic",
    "maximum_answer_length": 100
  },
  "post_processing": {
    "is_activated": true
  },
  "answer_formatting": {
    "waiting_messages_for_answer_generation": "Génération... \nSynthèse... \nRéponse... \nUn petit moment svp...",
    "waiting_messages_for_search": "Recherche... \nRecherche en cours... \nJ'interroge mon contexte... \nRecherche dans ma base de données... \nJe consulte mes ressources...",
    "waiting_messages_for_analysis": "Analyse... \nAnalyse de votre requête... \nTraitement votre requête... \nTraitement du message... \nAnalyse de votre demande... \nAnalyse en cours... \nTraitement de votre demande... \nCompréhension du message... \nInterprétation en cours... \nÉvaluation de la requête..."
  },
  "source": {
    "sources": [
      {
        "name": "string up",
        "_id": "66716edc649a8d158495d425"
      }
    ]
  },
  "search": {
    "strategy": "semantic",
    "similarity_threshold": 0.79,
    "number_best_results_llm_context": 4,
    "search_results_per_query": 10
  },
  "LLM": {
    "model_id": "66425829914fbb87228da576",
    "model_name": "gpt 4 o",
    "reuse_these_models": true
  },
  "type": "chat"
}

Changes

No recorded changes to this operation across all 1 revision of this API.