Reference

• langdash package
  • Subpackages
    • langdash.chains package
      • Submodules
      • langdash.chains.chains module
      • langdash.chains.nodes module
      • langdash.chains.typing module
      • Module contents
    • langdash.chat package
      • Submodules
      • langdash.chat.chat module
      • Module contents
    • langdash.classify package
      • Submodules
      • langdash.classify.token_qa module
      • Module contents
    • langdash.models package
      • Submodules
      • langdash.models.ctransformers module
      • langdash.models.llama_cpp module
      • langdash.models.rwkv_cpp module
      • langdash.models.sentence_transformers module
      • langdash.models.transformers module
      • Module contents
    • langdash.search package
      • Submodules
      • langdash.search.embedding_search module
      • langdash.search.engine module
      • langdash.search.multichoice_search module
      • Module contents
  • Submodules
  • langdash.core module
    • Langdash
      • Langdash.arg()
      • Langdash.chain()
      • Langdash.choice()
      • Langdash.format_args()
      • Langdash.model_from_type()
      • Langdash.register_model()
      • Langdash.repeat()
      • Langdash.returns()
      • Langdash.session_for_model()
      • Langdash.text()
  • langdash.infer module
    • InferArgs
      • InferArgs.max_new_tokens
      • InferArgs.max_rep_ctx
      • InferArgs.min_new_tokens
      • InferArgs.rep_penalty
      • InferArgs.rng
      • InferArgs.temperature
      • InferArgs.top_k
      • InferArgs.top_p
      • InferArgs.typical_mass
    • SpecialToken
  • langdash.llm module
    • EmbeddingLLM
      • EmbeddingLLM.capability
    • LLM
      • LLM.capability
      • LLM.session()
    • LLMCapability
  • langdash.llm_config module
    • LLMConfig
      • LLMConfig.model
      • LLMConfig.batch_size
      • LLMConfig.threads
      • LLMConfig.context_length
      • LLMConfig.gpu_layers
  • langdash.llm_session module
    • LLMEmbeddingSession
      • LLMEmbeddingSession.embed()
      • LLMEmbeddingSession.embedding_size
    • LLMGenerationSession
      • LLMGenerationSession.clone()
      • LLMGenerationSession.clone_state()
      • LLMGenerationSession.context_length
      • LLMGenerationSession.default_infer_args
      • LLMGenerationSession.event_handlers
      • LLMGenerationSession.get_vocab()
      • LLMGenerationSession.infer()
      • LLMGenerationSession.next_token_logits()
      • LLMGenerationSession.next_token_probs()
      • LLMGenerationSession.scratch_state()
      • LLMGenerationSession.set_state()
      • LLMGenerationSession.token_healing
      • LLMGenerationSession.tokenize()
      • LLMGenerationSession.tokenize_special()
      • LLMGenerationSession.tokens_used
    • LLMGenerationSessionForRawText
      • LLMGenerationSessionForRawText.flush_token()
      • LLMGenerationSessionForRawText.next_token_probs()
    • LLMSession
      • LLMSession.clone()
    • LLMState
  • langdash.logit_preprocessors module
    • LogitPreprocessor
  • langdash.response module
    • RespChoice
    • RespInfer
      • RespInfer.tokid
      • RespInfer.tokstr
      • RespInfer.running_infer
    • RespInferEnd
    • RespInject
      • RespInject.tokens_counter
    • RespReturns
      • RespReturns.key
    • RespSubchain
      • RespSubchain.key
      • RespSubchain.resp_subchain
    • Response
  • langdash.sampling module
    • logits_to_probs()
    • sample()
  • Module contents