Helper Functions & Constants

The Search module provides standalone helper functions for query preprocessing, document content preprocessing, and embedding model alias resolution, along with constants for model configuration.

1
from signalwire.search import (
2
    preprocess_query,
3
    preprocess_document_content,
4
    resolve_model_alias,
5
    MODEL_ALIASES,
6
    DEFAULT_MODEL,
7
)

Functions

preprocess_query

preprocess_query(query, language="en", pos_to_expand=None, max_synonyms=5, debug=False, vector=False, query_nlp_backend="nltk", model_name=None, preserve_original=True) -> dict[str, Any]

Preprocess a search query with language detection, tokenization, stop word removal, POS tagging, synonym expansion, stemming, and optional vectorization. This function is used internally by SearchService and SearchEngine but can also be called directly for custom search pipelines.

Parameters

Returns

dict[str, Any] — A dictionary containing:

• input (str) — the original query string as passed in
• enhanced_text (str) — the preprocessed query text with synonyms and stems
• language (str) — detected or specified language code
• POS (dict) — POS tag analysis results
• vector (list[float]) — embedding vector (only when vector=True)

Example

1
from signalwire.search import preprocess_query
2
3
# Basic preprocessing
4
result = preprocess_query("How do I configure voice agents?")
5
print(result["enhanced_text"])
6
7
# With vectorization for search
8
result = preprocess_query(
9
    "How do I configure voice agents?",
10
    vector=True,
11
    language="auto",
12
)
13
query_vector = result["vector"]
14
enhanced_text = result["enhanced_text"]

preprocess_document_content

preprocess_document_content(content, language="en", index_nlp_backend="nltk") -> dict[str, Any]

Preprocess document content for indexing. Uses less aggressive synonym expansion than query preprocessing to keep document representations focused.

This function is called internally by IndexBuilder during index construction.

Parameters

Returns

dict[str, Any] — A dictionary containing:

• enhanced_text (str) — the preprocessed document text
• keywords (list[str]) — up to 20 extracted keywords (stop words removed)
• language (str) — the language used for processing
• pos_analysis (dict) — POS tag analysis

Example

1
from signalwire.search import preprocess_document_content
2
3
result = preprocess_document_content(
4
    "SignalWire agents can be configured with custom prompts and tools.",
5
    language="en",
6
)
7
print(result["keywords"])
8
# ['signalwire', 'agents', 'configured', 'custom', 'prompts', 'tools']

resolve_model_alias

resolve_model_alias(model_name) -> str

Resolve a short model alias to its full model name. If the input is not a known alias, it is returned unchanged.

Parameters

Returns

str — The full sentence transformer model name.

Example

1
from signalwire.search import resolve_model_alias
2
3
print(resolve_model_alias("mini"))
4
# "sentence-transformers/all-MiniLM-L6-v2"
5
6
print(resolve_model_alias("sentence-transformers/all-mpnet-base-v2"))
7
# "sentence-transformers/all-mpnet-base-v2"  (unchanged)

Constants

MODEL_ALIASES

1
from signalwire.search import MODEL_ALIASES
2
3
print(MODEL_ALIASES)  # dict[str, str]

Dictionary mapping short model aliases to full sentence transformer model names.

DEFAULT_MODEL

1
from signalwire.search import DEFAULT_MODEL
2
3
print(DEFAULT_MODEL)  # "sentence-transformers/all-MiniLM-L6-v2"

The default embedding model used for new indexes. This is the "mini" model, chosen for its smaller size and faster inference. Use the "base" alias or specify a full model name when higher embedding quality is needed.