Config

Endpoint, URL, and Supported Methods

Objects are managed via the View Assistant server API at [http|https]://[hostname]:[port]/v1.0/tenants/[tenant-guid]/assistant

Supported methods include:GET HEAD POST PUT DELETE

Structure

{
    "GUID": "8d48511f-dc01-4b11-9eb7-f5bad86c482c",
    "Name": "botox",
    "Description": null,
    "SystemPrompt": "You are an AI assistant augmented with a retrieval system. Carefully analyze the provided pieces of context and the user query at the end. \n\nRely primarily on the provided context for your response. If the context is not enough for you to answer the question, please politely explain that you do not have enough relevant information to answer. \n\nDo not try to make up an answer. Do not attempt to answer using general knowledge.",
    "EmbeddingModel": "sentence-transformers/all-MiniLM-L6-v2",
    "MaxResults": 10,
    "VectorDatabaseName": "vectordb",
    "VectorDatabaseTable": "view-73871c0b-00cd-44f0-be5f-f5612523d8c5",
    "VectorDatabaseHostname": "pgvector",
    "VectorDatabasePort": 5432,
    "VectorDatabaseUser": "postgres",
    "VectorDatabasePassword": "password",
    "GenerationProvider": "ollama",
    "GenerationModel": "qwen2.5:latest",
    "GenerationApiKey": "",
    "Temperature": 0.1,
    "TopP": 0.95,
    "MaxTokens": 4000,
    "OllamaHostname": "192.168.86.250",
    "OllamaPort": 11434,
    "OllamaContextLength": null,
    "ContextSort": true,
    "SortBySimilarity": true,
    "ContextScope": 5,
    "Rerank": true,
    "RerankModel": "cross-encoder/ms-marco-MiniLM-L-6-v2",
    "RerankTopK": 5,
    "RerankLevel": "Chunk",
    "TimestampEnabled": true,
    "TimestampFormat": "Date",
    "TimestampTimezone": "UTC",
    "UseCitations": false,
    "CreatedUTC": "2025-04-11T19:05:56.694880",
    "LastModifiedUTC": "2025-04-11T19:05:56.694880",
    "ChatOnly": false
}

Properties

GUID string unique identifier for the configuration
Name string name of the assistant
Description string|null optional description of the assistant
SystemPrompt string initial system message that defines assistant behavior
EmbeddingModel string model used for embedding (e.g. sentence-transformers/all-MiniLM-L6-v2)
MaxResults number maximum number of results to retrieve from the vector database
VectorDatabaseName string name of the vector database
VectorDatabaseTable string table/view name used for querying vectors
VectorDatabaseHostname string hostname of the vector database
VectorDatabasePort number port number of the vector database
VectorDatabaseUser string username used to connect to the vector database
VectorDatabasePassword string password for the vector database
GenerationProvider string provider used for text generation (e.g. ollama)
GenerationModel string model used for generating text (e.g. qwen2.5:latest)
GenerationApiKey string API key used for the generation provider
Temperature number controls randomness in generation (higher = more random)
TopP number nucleus sampling threshold for token generation
MaxTokens number maximum number of tokens allowed in the response
OllamaHostname string hostname of the Ollama generation server
OllamaPort number port of the Ollama generation server
OllamaContextLength number|null max context window for Ollama (null for default)
ContextSort boolean whether to sort context entries
SortBySimilarity boolean whether to sort context entries by vector similarity
ContextScope number number of top context entries to include
Rerank boolean whether to apply a reranker model
RerankModel string model used for reranking results
RerankTopK number top K results to pass through reranker
RerankLevel string reranking granularity level (e.g. Chunk)
TimestampEnabled boolean whether to include timestamps in output
TimestampFormat string format for timestamp (e.g. Date, ISO)
TimestampTimezone string timezone for timestamp formatting (e.g. UTC)
UseCitations boolean whether to include citations in generated output
CreatedUTC datetime timestamp of creation in UTC
LastModifiedUTC datetime last modified timestamp in UTC
ChatOnly boolean whether this assistant is restricted to chat-only interactions

Create RAG config

To create, callPOST /v1.0/tenants/[tenant-guid]/assistant/configs

curl --location 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs' \
--header 'Content-Type: application/json' \
--data '{
    "Name": "Basic RAG Assistant",
    "Description": "uses qwen2.5:7b - ollama",
    "SystemPrompt": "Use the provided context to answer questions.",
    "EmbeddingModel": "sentence-transformers/all-MiniLM-L6-v2",
    "MaxResults": 10,
    "VectorDatabaseName": "vectordb",
    "VectorDatabaseTable": "minilm",
    "VectorDatabaseHostname": "pgvector",
    "VectorDatabasePort": 5432,
    "VectorDatabaseUser": "postgres",
    "VectorDatabasePassword": "password",
    "GenerationProvider": "ollama",
    "GenerationApiKey": "",
    "GenerationModel": "qwen2.5:7b",
    "HuggingFaceApiKey": "",
    "Temperature": 0.1,
    "TopP": 0.95,
    "MaxTokens": 500,
    "OllamaHostname": "ollama",
    "OllamaPort": 11434,
    "ContextSort": true,
    "SortByMaxSimilarity": true,
    "ContextScope": 0,
    "Rerank": true,
    "RerankModel": "cross-encoder/ms-marco-MiniLM-L-6-v2",
    "RerankTopK": 3
}'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const createAssistant = async () => {
  try {
    const response = await assistant.createAssistantConfig({
      Name: "Basic RAG Assistant",
      Description: "uses qwen2.5:7b - ollama",
      SystemPrompt: "Use the provided context to answer questions.",
      EmbeddingModel: "sentence-transformers/all-MiniLM-L6-v2",
      MaxResults: 10,
      VectorDatabaseName: "vectordb",
      VectorDatabaseTable: "minilm",
      VectorDatabaseHostname: "pgvector",
      VectorDatabasePort: 5432,
      VectorDatabaseUser: "postgres",
      VectorDatabasePassword: "password",
      GenerationProvider: "ollama",
      GenerationApiKey: "",
      GenerationModel: "qwen2.5:7b",
      HuggingFaceApiKey: "",
      Temperature: 0.1,
      TopP: 0.95,
      MaxTokens: 500,
      OllamaHostname: "ollama",
      OllamaPort: 11434,
      ContextSort: true,
      SortByMaxSimilarity: true,
      ContextScope: 0,
      Rerank: true,
      RerankModel: "cross-encoder/ms-marco-MiniLM-L-6-v2",
      RerankTopK: 3,
    });
    console.log(response);
  } catch (err) {
    console.log("Error creating assistant:", err);
  }
};

createAssistant();

Create chat only config

curl --location 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs' \
--header 'Content-Type: application/json' \
--data '{
    "Name": "Chat Only Blackbeard Assistant",
    "Description": "uses qwen2.5:7b - ollama",
    "SystemPrompt": "You are Edward Teach (c. 1680 – 22 November 1718), better known as the pirate Blackbeard. Talk like a pirate and only answer questions with period correct answers.",
    "GenerationProvider": "ollama",
    "GenerationApiKey": "",
    "GenerationModel": "qwen2.5:7b",
    "Temperature": 0.1,
    "TopP": 0.95,
    "MaxTokens": 500,
    "OllamaHostname": "ollama",
    "OllamaPort": 11434,
    "ChatOnly": true
}'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const createAssistant = async () => {
  try {
    const response = await assistant.createAssistantConfig({
      Name: "Chat Only Blackbeard Assistant",
      Description: "uses qwen2.5:7b - ollama",
      SystemPrompt:
        "You are Edward Teach (c. 1680 – 22 November 1718), better known as the pirate Blackbeard. Talk like a pirate and only answer questions with period correct answers.",
      GenerationProvider: "ollama",
      GenerationApiKey: "",
      GenerationModel: "qwen2.5:7b",
      Temperature: 0.1,
      TopP: 0.95,
      MaxTokens: 500,
      OllamaHostname: "ollama",
      OllamaPort: 11434,
      ChatOnly: true,
    });
    console.log(response);
  } catch (err) {
    console.log("Error creating assistant:", err);
  }
};

// createAssistant();

Read

To read config by GUID, call GET /v1.0/tenants/[tenant-guid]/assistant/configs/[config-guid]

curl --location 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs/8d48511f-dc01-4b11-9eb7-f5bad86c482c'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const readAssistant = async () => {
  try {
    const response = await assistant.retrieveAssistantConfig(
      "039c4efd-3907-425f-964e-5e6a5b5e1ebe"
    );
    console.log(response);
  } catch (err) {
    console.log("Error reading assistant:", err);
  }
};

readAssistant();

Read all

To read al configs, call GET /v1.0/tenants/[tenant-guid]/assistant/configs

curl --location 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const readAllConfigs = async () => {
  try {
    const response = await assistant.retrieveAssistantConfigs();
    console.log(response);
  } catch (err) {
    console.log("Error reading all configs:", err);
  }
};
readAllConfigs();

Response

{
    "AssistantConfigs": [
        {
            "GUID": "8d48511f-dc01-4b11-9eb7-f5bad86c482c",
            "Name": "botox",
            "Description": null,
            "CreatedUTC": "2025-04-11T19:05:56.713900Z"
        }
}

Update

To update a config by GUID, call PUT /v1.0/tenants/[tenant-guid]/assistant/configs/[config-guid]

curl --location --request PUT 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs/00000000-0000-0000-0000-000000000000' \
--header 'Content-Type: application/json' \
--data '{
    "Name": "Updated RAG Assistant",
    "Description": "uses qwen2.5:7b - ollama",
    "SystemPrompt": "Use the provided context to answer questions.",
    "EmbeddingModel": "sentence-transformers/all-MiniLM-L6-v2",
    "MaxResults": 10,
    "VectorDatabaseName": "vectordb",
    "VectorDatabaseTable": "minilm",
    "VectorDatabaseHostname": "pgvector",
    "VectorDatabasePort": 5432,
    "VectorDatabaseUser": "postgres",
    "VectorDatabasePassword": "password",
    "GenerationProvider": "ollama",
    "GenerationApiKey": "",
    "GenerationModel": "qwen2.5:7b",
    "HuggingFaceApiKey": "",
    "Temperature": 0.1,
    "TopP": 0.95,
    "MaxTokens": 500,
    "OllamaHostname": "ollama",
    "OllamaPort": 11434,
    "ContextSort": true,
    "SortByMaxSimilarity": true,
    "ContextScope": 0,
    "Rerank": true,
    "RerankModel": "cross-encoder/ms-marco-MiniLM-L-6-v2",
    "RerankTopK": 3
}'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);


const updateAssistantConfig = async () => {
  try {
    const response = await assistant.updateAssistantConfig({
      GUID: "039c4efd-3907-425f-964e-5e6a5b5e1ebe",
      Name: "Basic RAG Assistant [ASHISH_UPDATED]",
      Description: "uses qwen2.5:7b - ollama",
      SystemPrompt: "Use the provided context to answer questions.",
      EmbeddingModel: "sentence-transformers/all-MiniLM-L6-v2",
      MaxResults: 10,
      VectorDatabaseName: "vectordb",
      VectorDatabaseTable: "minilm",
      VectorDatabaseHostname: "pgvector",
      VectorDatabasePort: 5432,
      VectorDatabaseUser: "postgres",
      VectorDatabasePassword: "password",
      GenerationProvider: "ollama",
      GenerationModel: "qwen2.5:7b",
      GenerationApiKey: "",
      Temperature: 0.1,
      TopP: 0.95,
      MaxTokens: 500,
      OllamaHostname: "ollama",
      OllamaPort: 11434,
      OllamaContextLength: null,
      ContextSort: true,
      SortBySimilarity: true,
      ContextScope: 0,
      Rerank: true,
      RerankModel: "cross-encoder/ms-marco-MiniLM-L-6-v2",
      RerankTopK: 3,
      RerankLevel: "Chunk",
      TimestampEnabled: true,
      TimestampFormat: "Date",
      TimestampTimezone: "UTC",
      UseCitations: false,
      CreatedUTC: "2025-04-22T09:57:18.942204",
      LastModifiedUTC: "2025-04-22T09:57:18.942204",
      ChatOnly: false,
    });
    console.log(response);
  } catch (err) {
    console.log("Error updating assistant config:", err);
  }
};

updateAssistantConfig();

Delete

To read config by GUID, call DELETE /v1.0/tenants/[tenant-guid]/assistant/configs/[config-guid]

curl --location 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs/8d48511f-dc01-4b11-9eb7-f5bad86c482c'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const readAssistant = async () => {
  try {
    const response = await assistant.retrieveAssistantConfig(
      "039c4efd-3907-425f-964e-5e6a5b5e1ebe"
    );
    console.log(response);
  } catch (err) {
    console.log("Error reading assistant:", err);
  }
};

readAssistant();

Check existence

To check existence of a config by GUID, call HEAD /v1.0/tenants/[tenant-guid]/assistant/configs/[config-guid]

curl --location --head 'http://view.homedns.org:8000/v1.0/tenants/00000000-0000-0000-0000-000000000000/assistant/configs/00000000-0000-0000-0000-000000000000'

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

const existingAssistant = async () => {
  try {
    const response = await assistant.existsAssistantConfig(
      "039c4efd-3907-425f-964e-5e6a5b5e1ebe"
    );
    console.log(response);
  } catch (err) {
    console.log("Error retrieving assistant:", err);
  }
};
existingAssistant();