Skip to content
LLamaSharp Documentation
Langchain integration
Initializing search
LLamaSharp Documentation
Overview
Quick Start
Architecture
FAQ
Contributing Guide
Tutorials
Tutorials
Customize the native library loading
Use executors
Use ChatSession
Understand LLamaContext
Get embeddings
Quantize the model
Integrations
Integrations
semantic-kernel integration
kernel-memory integration
BotSharp integration
Langchain integration
Examples
Examples
Bacthed executor - multi-output to one input
Batched executor - basic guidance
Batched executor - rewinding to an earlier state
Chinese LLM - with GB2312 encoding
ChatSession - stripping role names
ChatSession - with history
ChatSession - restarting
ChatSession - Basic
Coding assistant
Get embeddings
Grammar - json response
Instruct executor - basic
Interactive executor - basic
Kernel memory integration - basic
Kernel-memory - save & load
LLaVA - basic
ChatSession - load & save
Executor - save/load state
Quantization
Semantic-kernel - chat
Semantic-kernel - with kernel-memory
Semantic-kernel - basic
Stateless executor
Talk to yourself
API Reference
API Reference
index
llama.abstractions.adaptercollection
llama.abstractions.icontextparams
llama.abstractions.ihistorytransform
llama.abstractions.iinferenceparams
llama.abstractions.illamaexecutor
llama.abstractions.illamaparams
llama.abstractions.imodelparams
llama.abstractions.itextstreamtransform
llama.abstractions.itexttransform
llama.abstractions.loraadapter
llama.abstractions.metadataoverride
llama.abstractions.metadataoverrideconverter
llama.abstractions.tensorsplitscollection
llama.abstractions.tensorsplitscollectionconverter
llama.antipromptprocessor
llama.batched.alreadypromptedconversationexception
llama.batched.batchedexecutor
llama.batched.cannotforkwhilerequiresinferenceexception
llama.batched.cannotmodifywhilerequiresinferenceexception
llama.batched.cannotsamplerequiresinferenceexception
llama.batched.cannotsamplerequirespromptexception
llama.batched.conversation
llama.batched.conversationextensions
llama.batched.experimentalbatchedexecutorexception
llama.chatsession-1
llama.chatsession
llama.common.authorrole
llama.common.chathistory
llama.common.fixedsizequeue-1
llama.common.inferenceparams
llama.common.mirostattype
llama.common.modelparams
llama.exceptions.grammarexpectedname
llama.exceptions.grammarexpectednext
llama.exceptions.grammarexpectedprevious
llama.exceptions.grammarformatexception
llama.exceptions.grammarunexpectedcharaltelement
llama.exceptions.grammarunexpectedcharrngelement
llama.exceptions.grammarunexpectedendelement
llama.exceptions.grammarunexpectedendofinput
llama.exceptions.grammarunexpectedhexcharscount
llama.exceptions.grammarunknownescapecharacter
llama.exceptions.llamadecodeerror
llama.exceptions.loadweightsfailedexception
llama.exceptions.runtimeerror
llama.extensions.icontextparamsextensions
llama.extensions.imodelparamsextensions
llama.grammars.grammar
llama.grammars.grammarrule
llama.ichatmodel
llama.llamacache
llama.llamaembedder
llama.llamamodel
llama.llamamodelv1
llama.llamaparams
llama.llamaquantizer
llama.llamastate
llama.llamatransforms
llama.llavaweights
llama.native.decoderesult
llama.native.ggmltype
llama.native.gpusplitmode
llama.native.llamabatch
llama.native.llamabeamsstate
llama.native.llamabeamview
llama.native.llamachatmessage
llama.native.llamacontextparams
llama.native.llamaftype
llama.native.llamagrammarelement
llama.native.llamagrammarelementtype
llama.native.llamakvcacheview
llama.native.llamakvcacheviewcell
llama.native.llamakvcacheviewsafehandle
llama.native.llamaloglevel
llama.native.llamamodelkvoverridetype
llama.native.llamamodelmetadataoverride
llama.native.llamamodelparams
llama.native.llamamodelquantizeparams
llama.native.llamanativebatch
llama.native.llamapoolingtype
llama.native.llamapos
llama.native.llamaropetype
llama.native.llamaseqid
llama.native.llamatoken
llama.native.llamatokendata
llama.native.llamatokendataarray
llama.native.llamatokendataarraynative
llama.native.llamatokentype
llama.native.llamavocabtype
llama.native.llavaimageembed
llama.native.nativeapi
llama.native.nativelibraryconfig
llama.native.ropescalingtype
llama.native.safellamacontexthandle
llama.native.safellamagrammarhandle
llama.native.safellamahandlebase
llama.native.safellamamodelhandle
llama.native.safellavaimageembedhandle
llama.native.safellavamodelhandle
llama.quantizer
llama.sampling.basesamplingpipeline
llama.sampling.defaultsamplingpipeline
llama.sampling.greedysamplingpipeline
llama.sampling.isamplingpipeline
llama.sampling.isamplingpipelineextensions
llama.sampling.mirostate2samplingpipeline
llama.sampling.mirostatesamplingpipeline
llama.sessionstate
llama.streamingtokendecoder
llama.types.chatcompletion
llama.types.chatcompletionchoice
llama.types.chatcompletionchunk
llama.types.chatcompletionchunkchoice
llama.types.chatcompletionchunkdelta
llama.types.chatcompletionmessage
llama.types.chatmessagerecord
llama.types.chatrole
llama.types.completion
llama.types.completionchoice
llama.types.completionchunk
llama.types.completionlogprobs
llama.types.completionusage
llama.types.embedding
llama.types.embeddingdata
llama.types.embeddingusage
logger
Langchain integration
The document is under work, please have a wait. Thank you for your support! :)