LLMUnity.Searchable Class Reference

Class implementing the search template. More...

Inheritance diagram for LLMUnity.Searchable:

Public Member Functions
string	Get (int key)
	Retrieves the phrase with the specific id.
Task< int >	Add (string inputString, string group="")
	Adds a phrase to the search.
int	Remove (string inputString, string group="")
	Removes a phrase from the search.
void	Remove (int key)
	Removes a phrase from the search.
int	Count ()
	Returns a count of the phrases.
int	Count (string group)
	Returns a count of the phrases in a specific data group.
void	Clear ()
	Clears the search object.
Task< int >	IncrementalSearch (string queryString, string group="")
	Allows to do search and retrieve results in batches (incremental search).
ValueTuple< int[], float[], bool >	IncrementalFetchKeys (int fetchKey, int k)
	Retrieves the most similar search results in batches (incremental search). The phrase keys and distances are retrieved, as well as a parameter that dictates whether the search is exhausted.
void	IncrementalSearchComplete (int fetchKey)
	Completes the search and clears the cached results for an incremental search.
async Task<(string[], float[])>	Search (string queryString, int k, string group="")
	Search for similar results to the provided query. The most similar results and their distances (dissimilarity) to the query are retrieved.
virtual ValueTuple< string[], float[], bool >	IncrementalFetch (int fetchKey, int k)
	Retrieves the most similar search results in batches (incremental search). The most similar results and their distances (dissimilarity) to the query are retrieved as well as a parameter that dictates whether the search is exhausted.
void	Save (string filePath)
	Saves the state of the search object.
async Task< bool >	Load (string filePath)
	Loads the state of the search object.

Detailed Description

Class implementing the search template.

Definition at line 21 of file Search.cs.

Member Function Documentation

Add()

Task< int > LLMUnity.Searchable.Add ( string inputString, string group = "" )

abstract

Adds a phrase to the search.

Parameters

inputString	input phrase
group	data group to add it to

Returns

phrase id

Count() [1/2]

int LLMUnity.Searchable.Count ( )

abstract

Returns a count of the phrases.

Returns

phrase count

Count() [2/2]

int LLMUnity.Searchable.Count ( string group )

abstract

Returns a count of the phrases in a specific data group.

Parameters

group

data group

Returns

phrase count

Get()

string LLMUnity.Searchable.Get ( int key )

abstract

Retrieves the phrase with the specific id.

Parameters

key

phrase id

Returns

phrase

IncrementalFetch()

virtual ValueTuple< string[], float[], bool > LLMUnity.Searchable.IncrementalFetch ( int fetchKey, int k )

inlinevirtual

Retrieves the most similar search results in batches (incremental search). The most similar results and their distances (dissimilarity) to the query are retrieved as well as a parameter that dictates whether the search is exhausted.

Parameters

fetchKey	incremental search key
k	number of results to retrieve

Returns

A tuple containing:

• Array of retrieved results (string[]).
• Array of distances for each result (float[]).
• bool indicating if the search is exhausted.

Reimplemented in LLMUnity.Chunking.

Definition at line 137 of file Search.cs.

IncrementalFetchKeys()

ValueTuple< int[], float[], bool > LLMUnity.Searchable.IncrementalFetchKeys ( int fetchKey, int k )

abstract

Retrieves the most similar search results in batches (incremental search). The phrase keys and distances are retrieved, as well as a parameter that dictates whether the search is exhausted.

Parameters

fetchKey	incremental search key
k	number of results to retrieve

Returns

A tuple containing:

• Array of retrieved keys (int[]).
• Array of distances for each result (float[]).
• bool indicating if the search is exhausted.

IncrementalSearch()

Task< int > LLMUnity.Searchable.IncrementalSearch ( string queryString, string group = "" )

abstract

Allows to do search and retrieve results in batches (incremental search).

Parameters

queryString	search query
group	data group to search in

Returns

incremental search key

IncrementalSearchComplete()

void LLMUnity.Searchable.IncrementalSearchComplete ( int fetchKey )

abstract

Completes the search and clears the cached results for an incremental search.

Parameters

fetchKey

incremental search key

Load()

async Task< bool > LLMUnity.Searchable.Load ( string filePath )

inline

Loads the state of the search object.

Parameters

archive

file to load from

Definition at line 166 of file Search.cs.

Remove() [1/2]

void LLMUnity.Searchable.Remove ( int key )

abstract

Removes a phrase from the search.

Parameters

key

phrase id

Remove() [2/2]

int LLMUnity.Searchable.Remove ( string inputString, string group = "" )

abstract

Removes a phrase from the search.

Parameters

inputString	input phrase
group	data group to remove it from

Returns

number of removed entries/returns>

Save()

void LLMUnity.Searchable.Save ( string filePath )

inline

Saves the state of the search object.

Parameters

archive

file to save to

Definition at line 149 of file Search.cs.

Search()

async Task<(string[], float[])> LLMUnity.Searchable.Search ( string queryString, int k, string group = "" )

inline

Search for similar results to the provided query. The most similar results and their distances (dissimilarity) to the query are retrieved.

Parameters

queryString	query
k	number of results to retrieve
group	data group to search in

Returns

A tuple containing:

• Array of retrieved results (string[]).
• Array of distances for each result (float[]).
• bool indicating if the search is exhausted.

Definition at line 115 of file Search.cs.

---

The documentation for this class was generated from the following file:

• Runtime/RAG/Search.cs