Skip to content
Letta Platform Letta Platform Letta Docs
Sign up
API Reference

Passages

Search Passages
POST/v1/passages/search
ModelsExpand Collapse
Passage object { embedding, embedding_config, text, 12 more }

Representation of a passage, which is stored in archival memory.

embedding: array of number

The embedding of the passage.

embedding_config: EmbeddingConfig { embedding_dim, embedding_endpoint_type, embedding_model, 7 more }

Configuration for embedding model connection and processing parameters.

embedding_dim: number

The dimension of the embedding.

embedding_endpoint_type: "openai" or "anthropic" or "bedrock" or 16 more

The endpoint type for the model.

One of the following:
"openai"
"anthropic"
"bedrock"
"google_ai"
"google_vertex"
"azure"
"groq"
"ollama"
"webui"
"webui-legacy"
"lmstudio"
"lmstudio-legacy"
"llamacpp"
"koboldcpp"
"vllm"
"hugging-face"
"mistral"
"together"
"pinecone"
embedding_model: string

The model for the embedding.

azure_deployment: optional string

The Azure deployment for the model.

azure_endpoint: optional string

The Azure endpoint for the model.

azure_version: optional string

The Azure version for the model.

batch_size: optional number

The maximum batch size for processing embeddings.

embedding_chunk_size: optional number

The chunk size of the embedding.

embedding_endpoint: optional string

The endpoint for the model (None if local).

handle: optional string

The handle for this config, in the format provider/model-name.

text: string

The text of the passage.

id: optional string

The human-friendly ID of the Passage

archive_id: optional string

The unique identifier of the archive containing this passage.

created_at: optional string

The creation date of the passage.

formatdate-time
created_by_id: optional string

The id of the user that made this object.

file_id: optional string

The unique identifier of the file associated with the passage.

file_name: optional string

The name of the file (only for source passages).

is_deleted: optional boolean

Whether this passage is deleted or not.

last_updated_by_id: optional string

The id of the user that made this object.

metadata: optional map[unknown]

The metadata of the passage.

Deprecatedsource_id: optional string

Deprecated: Use folder_id field instead. The data source of the passage.

tags: optional array of string

Tags associated with this passage.

updated_at: optional string

The timestamp when the object was last updated.

formatdate-time
PassageSearchResponse = array of object { passage, score, metadata }
passage: Passage { embedding, embedding_config, text, 12 more }

The passage object

embedding: array of number

The embedding of the passage.

embedding_config: EmbeddingConfig { embedding_dim, embedding_endpoint_type, embedding_model, 7 more }

Configuration for embedding model connection and processing parameters.

embedding_dim: number

The dimension of the embedding.

embedding_endpoint_type: "openai" or "anthropic" or "bedrock" or 16 more

The endpoint type for the model.

One of the following:
"openai"
"anthropic"
"bedrock"
"google_ai"
"google_vertex"
"azure"
"groq"
"ollama"
"webui"
"webui-legacy"
"lmstudio"
"lmstudio-legacy"
"llamacpp"
"koboldcpp"
"vllm"
"hugging-face"
"mistral"
"together"
"pinecone"
embedding_model: string

The model for the embedding.

azure_deployment: optional string

The Azure deployment for the model.

azure_endpoint: optional string

The Azure endpoint for the model.

azure_version: optional string

The Azure version for the model.

batch_size: optional number

The maximum batch size for processing embeddings.

embedding_chunk_size: optional number

The chunk size of the embedding.

embedding_endpoint: optional string

The endpoint for the model (None if local).

handle: optional string

The handle for this config, in the format provider/model-name.

text: string

The text of the passage.

id: optional string

The human-friendly ID of the Passage

archive_id: optional string

The unique identifier of the archive containing this passage.

created_at: optional string

The creation date of the passage.

formatdate-time
created_by_id: optional string

The id of the user that made this object.

file_id: optional string

The unique identifier of the file associated with the passage.

file_name: optional string

The name of the file (only for source passages).

is_deleted: optional boolean

Whether this passage is deleted or not.

last_updated_by_id: optional string

The id of the user that made this object.

metadata: optional map[unknown]

The metadata of the passage.

Deprecatedsource_id: optional string

Deprecated: Use folder_id field instead. The data source of the passage.

tags: optional array of string

Tags associated with this passage.

updated_at: optional string

The timestamp when the object was last updated.

formatdate-time
score: number

Relevance score

metadata: optional map[unknown]

Additional metadata about the search result