sobelio/llm-chain

Issues

• Support for Anthropic?

  #301 opened 3 months ago by sayanb
  0

• Integration with GenAI crate?

  #300 opened 4 months ago by Boscop
  0

• Is there a way to run GGUF models?

  #295 opened 7 months ago by tirithen
  1

• Core dump when trying to run llama based model (vicuna)

  #294 opened 7 months ago by dixxe
  0

• `cargo check` failed to compile `time` lib when run in the root directory

  #292 opened 7 months ago by ghislaine-laios
  0

• Add support for huggingface embeddings

  #291 opened 8 months ago by joshpopelka20gmail
  0

• Add dev container to repo

  #290 opened 8 months ago by dfberry
  4

• Suppress LLAMA model param output on executor creation

  #289 opened 8 months ago by pyroraptor07
  0

• Support for Baidu Qianfan(Ernie/Wenxin) endpoint

  #288 opened 9 months ago by chenwanqq
  0

• Problem with "Tutorial: Getting Started using the LLAMA driver"

  #218 opened a year ago by josephleblanc
  6

• Transfer crates.io name langchain to this project

  #286 opened 9 months ago by kvnvelasco
  2

• How do we do custom id for llm-chain-milvus

  #284 opened 9 months ago by BadMask121
  0

• Possibility a good idea to replace llama.cpp with candle to run quantized models?

  #276 opened 10 months ago by andychenbruce
  1

• Add support for Baidu Qianfan(Wenxin Yiyan, Ernie, etc.) models

  #277 opened 10 months ago by chenwanqq
  0

• Add support for setting Open Api Base Url in options!

  #271 opened a year ago by prabirshrestha
  0

• add support of Ollama

  #265 opened a year ago by prabirshrestha
  10

• Compile Failed for llm-chain-llama-sys & llm-chain-llama

  #248 opened a year ago by harshvishu
  6

• How to modify OpenAI API endpoint?

  #255 opened a year ago by overheat
  1

• Pre-compiled llama.cpp

  #263 opened a year ago by CMorrison82z
  1

• support LCEL in langchain?

  #253 opened a year ago by npuichigo
  0

• LLM Memory

  #214 opened a year ago by ragyabraham
  1

• add support for Mistral using TGI / vllm / candle

  #225 opened a year ago by pabl-o-ce
  4

• Chain conversation: ability to send a message and receive a stream feature request

  #231 opened a year ago by JohnTheCoolingFan
  2

• Add support for Milvus vector DB

  #146 opened a year ago by Pablo1785
  1

• Problem with map reduce tutorial

  #211 opened a year ago by jacohend
  0

• Qdrant VectorStore: ability to set filters for querying

  #228 opened a year ago by JohnTheCoolingFan
  0

• How to only add_{texts,documents} if they aren't already in the vector store?

  #232 opened a year ago by nathaniel-brough
  2

• LLaMA utf-8 problems

  #187 opened a year ago by andychenbruce
  1

• Minimum supported Rust version?

  #191 opened a year ago by shinglyu
  1

• Access intermediary step results

  #168 opened 2 years ago by b0xtch
  2

• llm_chain_local: FieldRequiredError on example

  #147 opened 2 years ago by leonardohn
  6

• Wrong struct size on llm-chain-llama-sys when compiling with cuda support, causes segfault on FFI call

  #174 opened 2 years ago by andychenbruce
  2

• Cannot Compile

  #164 opened 2 years ago by Jessie-Wilkins
  2

• Add Chatgpt function call support

  #157 opened 2 years ago by DaviRain-Su
  5

• Index Loading not working if dumped from different process

  #154 opened 2 years ago by KCaverly
  3

• Implement ReACt agent

  #151 opened 2 years ago by Pablo1785
  0

• example folder disappeared but not mentioned in README

  #141 opened 2 years ago by AndyJado
  0

• Add support for llm-mpt

  #144 opened 2 years ago by panosAthDBX
  0

• Fix problem with map-reduce tutorial

  #110 opened 2 years ago by williamhogman
  10

• Can't update llama.cpp with latest bindings.

  #115 opened 2 years ago by Juzov
  0

• Executor returned by llm_chain_openai::chatgpt::Executor::for_client() does not implement llm_chain::traits::Executor ([E0277])

  #118 opened 2 years ago by AnthonyMichaelTDM
  3

• Add methods for estimating token use for Conversation chains

  #111 opened 2 years ago by williamhogman
  0

• LLama ChatConversations should evaluate and inject "Assistant:"

  #104 opened 2 years ago by Juzov
  0

• Add usage info to output

  #109 opened 2 years ago by williamhogman
  0

• Allow setting the model for openai

  #107 opened 2 years ago by williamhogman
  1

• Prompt builder UI

  #96 opened 2 years ago by williamhogman
  0

• Prompt formatting, parameters, and dynformat

  #83 opened 2 years ago by DMJ16
  2

• Make convenience macro for Parameters

  #77 opened 2 years ago by williamhogman
  0

• Make macro for creating executors

  #78 opened 2 years ago by williamhogman
  0

• Improve error handling around Tools

  #68 opened 2 years ago by Pablo1785
  3