swiss_army_llama
LLM toolset
A FastAPI service that facilitates semantic text search using precomputed embeddings and advanced similarity measures.
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
947 stars
16 watching
55 forks
Language: Python
last commit: 4 months ago
Linked from 2 awesome lists
embedding-similarityembedding-vectorsembeddingsllama2llamacppsemantic-search
hannibal046/awesome-llm
kyrolabs/awesome-langchainRelated projects:
| Repository | Description | Stars |
|---|---|---|
 snunez1/llama.cl | A Common Lisp port of a Large Language Model (LLM) implementation | 36 |
 run-llama/llamaindexts | A data framework for integrating large language models into applications with custom data | 1,997 |
 victordibia/llmx | An API that provides a unified interface to multiple large language models for chat fine-tuning | 79 |
 melih-unsal/demogpt | A comprehensive toolset for building Large Language Model (LLM) based applications | 1,733 |
 msoedov/langcorn | A framework for serving large language models with a robust and efficient API | 909 |
 jetxu-llm/llama-github | Empowers AI-driven applications to retrieve relevant code snippets and repository information from GitHub using LLM-powered question analysis | 258 |
 damo-nlp-sg/m3exam | A benchmark for evaluating large language models in multiple languages and formats | 93 |
 pors/langchain-chat-websockets | An open-source chat application using LangChain and FastAPI that enables real-time conversations with an LLM | 91 |
 linksoul-ai/chinese-llama-2-7b | A deep learning project providing an open-source implementation of the LLaMA2 model with Chinese and English text data | 2,235 |
 aiplanethub/beyondllm | An open-source toolkit for building and evaluating large language models | 267 |
 km1994/llmsninestorydemontower | Exploring various LLMs and their applications in natural language processing and related areas | 1,854 |
 ai-hypercomputer/maxtext | A high-performance LLM written in Python/Jax for training and inference on Google Cloud TPUs and GPUs. | 1,557 |
 deepseek-ai/deepseek-moe | A large language model with improved efficiency and performance compared to similar models | 1,024 |
 blackhc/llm-strategy | Decouples software implementation from underlying logic using LLMs to automate parsing of structured data | 392 |
 ngxson/wllama | A WebAssembly binding for the LLaMA model that enables on-browser inference without requiring a backend or GPU. | 465 |