Skip to content

Get Full Session

ChatRetrieveResponse Beta.Chat.Retrieve(ChatRetrieveParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/chat/{session_id}

Retrieve a full session by ID, including its event history.

ParametersExpand Collapse
ChatRetrieveParams parameters
required string sessionID
string? organizationID
string? projectID
ReturnsExpand Collapse
class ChatRetrieveResponse:

Full chat session including its complete event history.

required IReadOnlyList<Event> Events

Ordered list of events that make up the conversation history.

One of the following:
class Stop:
required string? Error
required Boolean IsError
required Usage Usage
Double DurationMs
Long? TotalInputTokens
Long? TotalOutputTokens
Long Turns
Type Type
class TextDelta:
required string Content
Type Type
class Text:
required string Content
Type Type
class ThinkingDelta:
required string Content
Type Type
class Thinking:
required string Content
Type Type
class ToolCall:
required IReadOnlyDictionary<string, JsonElement> Arguments
required string CallID
required string Name
Type Type
class ToolResult:
required string CallID
required string Name
required JsonElement Result
ImageAttachment? ImageAttachment

Coordinates for lazily resolving a page screenshot presigned URL.

required string AttachmentName
required string SourceID
Type Type
class UserInput:
required string Content
Type Type
required string LastUpdatedAt

ISO-format timestamp showing when the session was last updated.

required string SessionID

Unique session identifier.

string? GeneratedTitle

Auto-generated title derived from the first user message.

IReadOnlyList<string>? IndexIds

Indexes this session is bound to. Null on unbound sessions.

JobMetadata? JobMetadata

Token usage and status from the most recent run. Null if the session has not been run yet.

Double DurationMs
string? Error
IReadOnlyList<string>? ExportConfigIds
Boolean IsError
Long? TotalInputTokens
Long? TotalOutputTokens
Long Turns

Get Full Session

ChatRetrieveParams parameters = new() { SessionID = "session_id" };

var chat = await client.Beta.Chat.Retrieve(parameters);

Console.WriteLine(chat);
{
  "events": [
    {
      "error": "error",
      "is_error": true,
      "usage": {
        "duration_ms": 0,
        "total_input_tokens": 0,
        "total_output_tokens": 0,
        "turns": 0
      },
      "type": "stop"
    }
  ],
  "last_updated_at": "2026-04-22T12:34:41.342245",
  "session_id": "ses-abc123",
  "generated_title": "What were the main findings in Q3?...",
  "index_ids": [
    "idx-abc123",
    "idx-def456"
  ],
  "job_metadata": {
    "duration_ms": 0,
    "error": "error",
    "export_config_ids": [
      "string"
    ],
    "is_error": true,
    "total_input_tokens": 0,
    "total_output_tokens": 0,
    "turns": 0
  }
}
Returns Examples
{
  "events": [
    {
      "error": "error",
      "is_error": true,
      "usage": {
        "duration_ms": 0,
        "total_input_tokens": 0,
        "total_output_tokens": 0,
        "turns": 0
      },
      "type": "stop"
    }
  ],
  "last_updated_at": "2026-04-22T12:34:41.342245",
  "session_id": "ses-abc123",
  "generated_title": "What were the main findings in Q3?...",
  "index_ids": [
    "idx-abc123",
    "idx-def456"
  ],
  "job_metadata": {
    "duration_ms": 0,
    "error": "error",
    "export_config_ids": [
      "string"
    ],
    "is_error": true,
    "total_input_tokens": 0,
    "total_output_tokens": 0,
    "turns": 0
  }
}
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/