MCPcopy Create free account

hub / github.com/abetlen/llama-cpp-python / endpoints

Endpoints95 in github.com/abetlen/llama-cpp-python

Routecount_query_tokens
router.post( "/extras/tokenize/count", summary="Tokenize Count", dependencies=[Depends(authenticat
llama_cpp/server/app.py:None
Routecreate_chat_completion
router.post( "/v1/chat/completions", summary="Chat", dependencies=[Depends(authenticate)], res
llama_cpp/server/app.py:None
Routecreate_chat_completion
app.post("/v1/chat/completions")
examples/server/server.py:None
Routecreate_chat_completions
app.post("/v1/chat/completions")
examples/batch-processing/server.py:None
Routecreate_completion
router.post( "/v1/completions", summary="Completion", dependencies=[Depends(authenticate)], re
llama_cpp/server/app.py:None
Routecreate_completion
app.post("/v1/completions")
examples/server/server.py:None
Routecreate_embedding
router.post( "/v1/embeddings", summary="Embedding", dependencies=[Depends(authenticate)], tags
llama_cpp/server/app.py:None
Routecreate_embedding
app.post("/v1/embeddings", response_model=CreateEmbeddingResponse)
examples/server/server.py:None
Routecreate_response
app.post("/v1/responses")
examples/server/server.py:None
Routedetokenize
router.post( "/extras/detokenize", summary="Detokenize", dependencies=[Depends(authenticate)],
llama_cpp/server/app.py:None
Routeget_models
router.get( "/v1/models", summary="Models", dependencies=[Depends(authenticate)], tags=[openai
llama_cpp/server/app.py:None
Routehealthz
app.get("/healthz", response_model=HealthzResponse)
examples/server/server.py:None
Routelist_models
app.get("/v1/models", response_model=ModelListResponse)
examples/server/server.py:None
Routellama_adapter_get_alora_invocation_tokens
ctypes_function( "llama_adapter_get_alora_invocation_tokens", [llama_adapter_lora_p_ctypes], ctype
llama_cpp/llama_cpp.py:None
Routellama_adapter_get_alora_n_invocation_tokens
ctypes_function( "llama_adapter_get_alora_n_invocation_tokens", [llama_adapter_lora_p_ctypes], cty
llama_cpp/llama_cpp.py:None
Routellama_batch_get_one
ctypes_function( "llama_batch_get_one", [ llama_token_p, ctypes.c_int32, ], ll
llama_cpp/llama_cpp.py:None
Routellama_get_ctx_other
_ctypes_function_from_names( ( "llama_get_ctx_other", "_Z19llama_get_ctx_otherP13llama_con
llama_cpp/llama_cpp_ext.py:None
Routellama_get_embeddings
ctypes_function( "llama_get_embeddings", [llama_context_p_ctypes], ctypes.POINTER(ctypes.c_float) )
llama_cpp/llama_cpp.py:None
Routellama_get_embeddings_ith
ctypes_function( "llama_get_embeddings_ith", [llama_context_p_ctypes, ctypes.c_int32], ctypes.POIN
llama_cpp/llama_cpp.py:None
Routellama_get_embeddings_nextn
_ctypes_function_from_names( ( "llama_get_embeddings_nextn", "_Z26llama_get_embeddings_nex
llama_cpp/llama_cpp_ext.py:None
Routellama_get_embeddings_nextn_ith
_ctypes_function_from_names( ( "llama_get_embeddings_nextn_ith", "_Z30llama_get_embeddings
llama_cpp/llama_cpp_ext.py:None
Routellama_get_embeddings_seq
ctypes_function( "llama_get_embeddings_seq", [llama_context_p_ctypes, llama_seq_id], ctypes.POINTE
llama_cpp/llama_cpp.py:None
Routellama_get_logits
ctypes_function( "llama_get_logits", [llama_context_p_ctypes], ctypes.POINTER(ctypes.c_float) )
llama_cpp/llama_cpp.py:None
Routellama_get_logits_ith
ctypes_function( "llama_get_logits_ith", [llama_context_p_ctypes, ctypes.c_int32], ctypes.POINTER(
llama_cpp/llama_cpp.py:None
Routellama_get_memory
ctypes_function("llama_get_memory", [llama_context_p_ctypes], llama_memory_t_ctypes)
llama_cpp/llama_cpp.py:None
Routellama_get_model
ctypes_function("llama_get_model", [llama_context_p_ctypes], llama_model_p_ctypes)
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_candidates_count_ith
ctypes_function( "llama_get_sampled_candidates_count_ith", [llama_context_p_ctypes, ctypes.c_int32],
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_candidates_ith
ctypes_function( "llama_get_sampled_candidates_ith", [llama_context_p_ctypes, ctypes.c_int32], cty
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_logits_count_ith
ctypes_function( "llama_get_sampled_logits_count_ith", [llama_context_p_ctypes, ctypes.c_int32], c
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_logits_ith
ctypes_function( "llama_get_sampled_logits_ith", [llama_context_p_ctypes, ctypes.c_int32], ctypes.
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_probs_count_ith
ctypes_function( "llama_get_sampled_probs_count_ith", [llama_context_p_ctypes, ctypes.c_int32], ct
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_probs_ith
ctypes_function( "llama_get_sampled_probs_ith", [llama_context_p_ctypes, ctypes.c_int32], ctypes.P
llama_cpp/llama_cpp.py:None
Routellama_get_sampled_token_ith
ctypes_function( "llama_get_sampled_token_ith", [llama_context_p_ctypes, ctypes.c_int32], llama_token )
llama_cpp/llama_cpp.py:None
Routellama_get_state_size
ctypes_function("llama_get_state_size", [llama_context_p_ctypes], ctypes.c_size_t)
llama_cpp/llama_cpp.py:None
Routellama_log_get
ctypes_function( "llama_log_get", [ctypes.POINTER(llama_log_callback), ctypes.POINTER(ctypes.c_void_p)
llama_cpp/llama_cpp.py:None
Routellama_model_get_vocab
ctypes_function("llama_model_get_vocab", [llama_model_p_ctypes], llama_vocab_p_ctypes)
llama_cpp/llama_cpp.py:None
Routellama_sampler_chain_get
ctypes_function( "llama_sampler_chain_get", [llama_sampler_p_ctypes, ctypes.c_int32], llama_sample
llama_cpp/llama_cpp.py:None
Routellama_sampler_get_seed
ctypes_function( "llama_sampler_get_seed", [llama_sampler_p_ctypes], ctypes.c_uint32, )
llama_cpp/llama_cpp.py:None
Routellama_state_get_data
ctypes_function( "llama_state_get_data", [ llama_context_p_ctypes, ctypes.POINTER(ctyp
llama_cpp/llama_cpp.py:None
Routellama_state_get_size
ctypes_function("llama_state_get_size", [llama_context_p_ctypes], ctypes.c_size_t)
llama_cpp/llama_cpp.py:None
Routellama_state_seq_get_data
ctypes_function( "llama_state_seq_get_data", [ llama_context_p_ctypes, ctypes.POINTER(
llama_cpp/llama_cpp.py:None
Routellama_state_seq_get_data_ext
ctypes_function( "llama_state_seq_get_data_ext", [ llama_context_p_ctypes, ctypes.POIN
llama_cpp/llama_cpp.py:None
Routellama_state_seq_get_size
ctypes_function( "llama_state_seq_get_size", [llama_context_p_ctypes, llama_seq_id], ctypes.c_size
llama_cpp/llama_cpp.py:None
Routellama_state_seq_get_size_ext
ctypes_function( "llama_state_seq_get_size_ext", [llama_context_p_ctypes, llama_seq_id, llama_state_se
llama_cpp/llama_cpp.py:None
Routellama_token_get_attr
ctypes_function( "llama_token_get_attr", [llama_vocab_p_ctypes, llama_token], ctypes.c_int, )
llama_cpp/llama_cpp.py:None
Routellama_token_get_score
ctypes_function( "llama_token_get_score", [llama_vocab_p_ctypes, llama_token], ctypes.c_float, )
llama_cpp/llama_cpp.py:None
Routellama_token_get_text
ctypes_function( "llama_token_get_text", [llama_vocab_p_ctypes, llama_token], ctypes.c_char_p, )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_add_bos
ctypes_function( "llama_vocab_get_add_bos", [llama_vocab_p_ctypes], ctypes.c_bool, )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_add_eos
ctypes_function( "llama_vocab_get_add_eos", [llama_vocab_p_ctypes], ctypes.c_bool, )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_add_sep
ctypes_function( "llama_vocab_get_add_sep", [llama_vocab_p_ctypes], ctypes.c_bool, )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_attr
ctypes_function( "llama_vocab_get_attr", [llama_vocab_p_ctypes, llama_token], ctypes.c_int )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_score
ctypes_function( "llama_vocab_get_score", [llama_vocab_p_ctypes, llama_token], ctypes.c_float )
llama_cpp/llama_cpp.py:None
Routellama_vocab_get_text
ctypes_function( "llama_vocab_get_text", [llama_vocab_p_ctypes, llama_token], ctypes.c_char_p )
llama_cpp/llama_cpp.py:None
Routemetrics
app.get("/metrics")
examples/server/server.py:None
Routemtmd_batch_add_chunk
ctypes_function( "mtmd_batch_add_chunk", [mtmd_batch_p_ctypes, mtmd_input_chunk_p_ctypes], c_int,
llama_cpp/mtmd_cpp.py:None
Routemtmd_batch_get_output_embd
ctypes_function( "mtmd_batch_get_output_embd", [mtmd_batch_p_ctypes, mtmd_input_chunk_p_ctypes], P
llama_cpp/mtmd_cpp.py:None
Routemtmd_bitmap_get_data
ctypes_function("mtmd_bitmap_get_data", [mtmd_bitmap_p_ctypes], POINTER(c_uint8))
llama_cpp/mtmd_cpp.py:None
Routemtmd_bitmap_get_id
ctypes_function("mtmd_bitmap_get_id", [mtmd_bitmap_p_ctypes], c_char_p)
llama_cpp/mtmd_cpp.py:None
Routemtmd_bitmap_get_n_bytes
ctypes_function("mtmd_bitmap_get_n_bytes", [mtmd_bitmap_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_bitmap_get_nx
ctypes_function("mtmd_bitmap_get_nx", [mtmd_bitmap_p_ctypes], c_uint32)
llama_cpp/mtmd_cpp.py:None
Routemtmd_bitmap_get_ny
ctypes_function("mtmd_bitmap_get_ny", [mtmd_bitmap_p_ctypes], c_uint32)
llama_cpp/mtmd_cpp.py:None
Routemtmd_decode_use_non_causal
ctypes_function( "mtmd_decode_use_non_causal", [mtmd_context_p_ctypes, mtmd_input_chunk_p_ctypes],
llama_cpp/mtmd_cpp.py:None
Routemtmd_encode_chunk
ctypes_function( "mtmd_encode_chunk", [mtmd_context_p_ctypes, mtmd_input_chunk_p_ctypes], c_int, )
llama_cpp/mtmd_cpp.py:None
Routemtmd_get_audio_sample_rate
ctypes_function("mtmd_get_audio_sample_rate", [mtmd_context_p_ctypes], c_int)
llama_cpp/mtmd_cpp.py:None
Routemtmd_get_cap_from_file
ctypes_function("mtmd_get_cap_from_file", [c_char_p], mtmd_caps)
llama_cpp/mtmd_cpp.py:None
Routemtmd_get_marker
ctypes_function("mtmd_get_marker", [mtmd_context_p_ctypes], c_char_p)
llama_cpp/mtmd_cpp.py:None
Routemtmd_get_output_embd
ctypes_function("mtmd_get_output_embd", [mtmd_context_p_ctypes], POINTER(c_float))
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_decode_image_chunk
ctypes_function( "mtmd_helper_decode_image_chunk", [ mtmd_context_p_ctypes, llama_cpp.
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_eval_chunk_single
ctypes_function( "mtmd_helper_eval_chunk_single", [ mtmd_context_p_ctypes, llama_cpp.l
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_eval_chunks
ctypes_function( "mtmd_helper_eval_chunks", [ mtmd_context_p_ctypes, llama_cpp.llama_c
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_get_n_pos
ctypes_function( "mtmd_helper_get_n_pos", [mtmd_input_chunks_p_ctypes], llama_cpp.llama_pos, )
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_get_n_tokens
ctypes_function("mtmd_helper_get_n_tokens", [mtmd_input_chunks_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_image_get_decoder_pos
ctypes_function( "mtmd_helper_image_get_decoder_pos", [mtmd_image_tokens_p_ctypes, llama_cpp.llama_pos
llama_cpp/mtmd_cpp.py:None
Routemtmd_helper_video_get_info
ctypes_function( "mtmd_helper_video_get_info", [mtmd_helper_video_p_ctypes], mtmd_helper_video_inf
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_decoder_pos
ctypes_function( "mtmd_image_tokens_get_decoder_pos", [mtmd_image_tokens_p_ctypes, llama_cpp.llama_pos
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_id
ctypes_function("mtmd_image_tokens_get_id", [mtmd_image_tokens_p_ctypes], c_char_p)
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_n_pos
ctypes_function( "mtmd_image_tokens_get_n_pos", [mtmd_image_tokens_p_ctypes], llama_cpp.llama_pos,
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_n_tokens
ctypes_function( "mtmd_image_tokens_get_n_tokens", [mtmd_image_tokens_p_ctypes], c_size_t )
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_nx
ctypes_function("mtmd_image_tokens_get_nx", [mtmd_image_tokens_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_image_tokens_get_ny
ctypes_function("mtmd_image_tokens_get_ny", [mtmd_image_tokens_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_copy
ctypes_function( "mtmd_input_chunk_copy", [mtmd_input_chunk_p_ctypes], mtmd_input_chunk_p_ctypes )
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_free
ctypes_function("mtmd_input_chunk_free", [mtmd_input_chunk_p_ctypes], None)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_id
ctypes_function("mtmd_input_chunk_get_id", [mtmd_input_chunk_p_ctypes], c_char_p)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_n_pos
ctypes_function( "mtmd_input_chunk_get_n_pos", [mtmd_input_chunk_p_ctypes], llama_cpp.llama_pos, )
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_n_tokens
ctypes_function("mtmd_input_chunk_get_n_tokens", [mtmd_input_chunk_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_tokens_image
ctypes_function( "mtmd_input_chunk_get_tokens_image", [mtmd_input_chunk_p_ctypes], mtmd_image_toke
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_tokens_text
ctypes_function( "mtmd_input_chunk_get_tokens_text", [mtmd_input_chunk_p_ctypes, POINTER(c_size_t)],
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunk_get_type
ctypes_function("mtmd_input_chunk_get_type", [mtmd_input_chunk_p_ctypes], c_int)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunks_free
ctypes_function("mtmd_input_chunks_free", [mtmd_input_chunks_p_ctypes], None)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunks_get
ctypes_function( "mtmd_input_chunks_get", [mtmd_input_chunks_p_ctypes, c_size_t], mtmd_input_chunk
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunks_init
ctypes_function("mtmd_input_chunks_init", [], mtmd_input_chunks_p_ctypes)
llama_cpp/mtmd_cpp.py:None
Routemtmd_input_chunks_size
ctypes_function("mtmd_input_chunks_size", [mtmd_input_chunks_p_ctypes], c_size_t)
llama_cpp/mtmd_cpp.py:None
Routemtmd_test_create_input_chunks
ctypes_function("mtmd_test_create_input_chunks", [], mtmd_input_chunks_p_ctypes)
llama_cpp/mtmd_cpp.py:None
Routemtmd_tokenize
ctypes_function( "mtmd_tokenize", [ mtmd_context_p_ctypes, mtmd_input_chunks_p_ctypes,
llama_cpp/mtmd_cpp.py:None
Routetokenize
router.post( "/extras/tokenize", summary="Tokenize", dependencies=[Depends(authenticate)], tag
llama_cpp/server/app.py:None