Skip to content

Create Session

beta.chat.create(ChatCreateParams**kwargs) -> ChatCreateResponse
POST/api/v1/chat

Create a chat session, optionally bound to indexes (locked after the first message).

ParametersExpand Collapse
organization_id: Optional[str]
project_id: Optional[str]
index_ids: Optional[SequenceNotStr[str]]

Indexes this session will retrieve from. Once set and the first message has been sent, the source set is locked for the session’s lifetime. Leave null to create an unbound session.

ReturnsExpand Collapse
class ChatCreateResponse:

Summary of a chat session, including its title and last run metadata.

last_updated_at: str

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

session_id: str

Unique session identifier.

generated_title: Optional[str]

Auto-generated title derived from the first user message.

index_ids: Optional[List[str]]

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

job_metadata: Optional[JobMetadata]

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

duration_ms: Optional[float]
error: Optional[str]
export_config_ids: Optional[List[str]]
is_error: Optional[bool]
total_input_tokens: Optional[int]
total_output_tokens: Optional[int]
turns: Optional[int]

Create Session

import os
from llama_cloud import LlamaCloud

client = LlamaCloud(
    api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),  # This is the default and can be omitted
)
chat = client.beta.chat.create()
print(chat.session_id)
{
  "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
{
  "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/python/shared/mcp/