Grep File

beta.retrieval.grep() -> RetrievalGrepResponse

POST/api/v1/retrieval/files/grep

Grep within a file’s parsed content using a regex pattern.

ParametersExpand Collapse

file_id: str

ID of the file to grep.

index_id: str

ID of the index the file belongs to.

pattern: str

Regex pattern to search for.

organization_id: Optional[str]

project_id: Optional[str]

context_chars: Optional[int]

Number of characters of context to include before and after the matched pattern in the content field of the response

limit: Optional[int]

Maximum number of matches to return.

ReturnsExpand Collapse

class RetrievalGrepResponse: …

Grep results for a file.

matches: List[Match]

Regex matches found in the file.

content: str

Matched text content.

end_char: int

End character offset of the match.

start_char: int

Start character offset of the match.

Grep File

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
)
response = client.beta.retrieval.grep(
    file_id="file_id",
    index_id="idx-abc123",
    pattern="revenue|profit",
)
print(response.matches)

{
  "matches": [
    {
      "content": "content",
      "end_char": 0,
      "start_char": 0
    }
  ]
}

Returns Examples

{
  "matches": [
    {
      "content": "content",
      "end_char": 0,
      "start_char": 0
    }
  ]
}