LLM for Unity  v2.3.0
Create characters in Unity with LLMs!
Loading...
Searching...
No Matches
Public Member Functions | List of all members
LLMUnity.Chunking Class Referenceabstract
RAG

Class implementing the chunking functionality. More...

Inheritance diagram for LLMUnity.Chunking:
[legend]

Public Member Functions

void ReturnChunks (bool returnChunks)
 Set to true to return chunks or the direct input with the Search function.
 
Task< List<(int, int)> > Split (string input)
 Splits the provided phrase into chunks.
 
override string Get (int key)
 Retrieves the phrase with the specific id.
 
override async Task< int > Add (string inputString, string group="")
 Adds a phrase to the search after splitting it into chunks.
 
override void Remove (int key)
 Removes a phrase and the phrase chunks from the search.
 
override int Remove (string inputString, string group="")
 Removes a phrase and the phrase chunks from the search.
 
override int Count ()
 Returns a count of the phrases.
 
override int Count (string group)
 Returns a count of the phrases in a specific data group.
 
override async Task< int > IncrementalSearch (string queryString, string group="")
 Allows to do search and retrieve results in batches (incremental search).
 
override ValueTuple< int[], float[], bool > IncrementalFetchKeys (int fetchKey, int k)
 Retrieves the most similar search results in batches (incremental search). The phrase/chunk keys and distances are retrieved, as well as a parameter that dictates whether the search is exhausted. The returnChunks variable defines whether to return chunks or phrases.
 
override ValueTuple< string[], float[], bool > IncrementalFetch (int fetchKey, int k)
 Retrieves the most similar search results in batches (incremental search). The phrases/chunks and their distances are retrieved, as well as a parameter that dictates whether the search is exhausted. The returnChunks variable defines whether to return chunks or phrases.
 
override void IncrementalSearchComplete (int fetchKey)
 Completes the search and clears the cached results for an incremental search.
 
override void Clear ()
 Clears the object and the associated search object.
 
- Public Member Functions inherited from LLMUnity.SearchPlugin
void SetSearch (SearchMethod search)
 Sets the search method of the plugin.
 
- Public Member Functions inherited from LLMUnity.Searchable
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.
 
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 chunking functionality.

Definition at line 17 of file Chunking.cs.

Member Function Documentation

◆ Add()

override async Task< int > LLMUnity.Chunking.Add ( string inputString,
string group = "" )
inline

Adds a phrase to the search after splitting it into chunks.

Parameters
inputStringinput phrase
groupdata group to add it to
Returns
phrase id

Definition at line 63 of file Chunking.cs.

◆ Clear()

override void LLMUnity.Chunking.Clear ( )
inline

Clears the object and the associated search object.

Definition at line 265 of file Chunking.cs.

◆ Count() [1/2]

override int LLMUnity.Chunking.Count ( )
inline

Returns a count of the phrases.

Returns
phrase count

Definition at line 147 of file Chunking.cs.

◆ Count() [2/2]

override int LLMUnity.Chunking.Count ( string group)
inline

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

Parameters
groupdata group
Returns
phrase count

Definition at line 157 of file Chunking.cs.

◆ Get()

override string LLMUnity.Chunking.Get ( int key)
inline

Retrieves the phrase with the specific id.

Parameters
keyphrase id
Returns
phrase

Definition at line 47 of file Chunking.cs.

◆ IncrementalFetch()

override ValueTuple< string[], float[], bool > LLMUnity.Chunking.IncrementalFetch ( int fetchKey,
int k )
inlinevirtual

Retrieves the most similar search results in batches (incremental search). The phrases/chunks and their distances are retrieved, as well as a parameter that dictates whether the search is exhausted. The returnChunks variable defines whether to return chunks or phrases.

Parameters
fetchKeyincremental search key
knumber of results to retrieve
Returns
A tuple containing:
  • Array of retrieved phrases/chunks (string[]).
  • Array of distances for each result (float[]).
  • bool indicating if the search is exhausted.

Reimplemented from LLMUnity.Searchable.

Definition at line 241 of file Chunking.cs.

◆ IncrementalFetchKeys()

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

Retrieves the most similar search results in batches (incremental search). The phrase/chunk keys and distances are retrieved, as well as a parameter that dictates whether the search is exhausted. The returnChunks variable defines whether to return chunks or phrases.

Parameters
fetchKeyincremental search key
knumber 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.

Definition at line 189 of file Chunking.cs.

◆ IncrementalSearch()

override async Task< int > LLMUnity.Chunking.IncrementalSearch ( string queryString,
string group = "" )
inline

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

Parameters
queryStringsearch query
groupdata group to search in
Returns
incremental search key

Definition at line 169 of file Chunking.cs.

◆ IncrementalSearchComplete()

override void LLMUnity.Chunking.IncrementalSearchComplete ( int fetchKey)
inline

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

Parameters
fetchKeyincremental search key

Definition at line 257 of file Chunking.cs.

◆ Remove() [1/2]

override void LLMUnity.Chunking.Remove ( int key)
inline

Removes a phrase and the phrase chunks from the search.

Parameters
keyphrase id

Definition at line 97 of file Chunking.cs.

◆ Remove() [2/2]

override int LLMUnity.Chunking.Remove ( string inputString,
string group = "" )
inline

Removes a phrase and the phrase chunks from the search.

Parameters
inputStringinput phrase
groupdata group to remove it from
Returns
number of removed phrases

Definition at line 130 of file Chunking.cs.

◆ ReturnChunks()

void LLMUnity.Chunking.ReturnChunks ( bool returnChunks)
inline

Set to true to return chunks or the direct input with the Search function.

Parameters
returnChunkswhether to return chunks

Definition at line 30 of file Chunking.cs.

◆ Split()

Task< List<(int, int)> > LLMUnity.Chunking.Split ( string input)
abstract

Splits the provided phrase into chunks.

Parameters
inputphrase
Returns
List of start/end indices of the split chunks
The documentation for this class was generated from the following file: