Source: https://seerepo.com/r/llmware-ai/llmware/built
Markdown source: https://seerepo.com/r/llmware-ai/llmware/built.md
Description: llmware is a Python repo built with Streamlit. It stores its data in Postgres and MongoDB. It has 71,264 written lines, with 18 test files.

# What is llmware built with?

llmware is a Python repo built with Streamlit. It stores its data in Postgres and MongoDB, uses AI through einops, datasets, torch, transformers, tokenizers, and 1 more, deploys with boto3, and uses chromadb, pgvector, psycopg, psycopg-binary, pymongo, and 2 more. It has 71,264 written lines, with 18 test files.

Read on November 8, 2026, at commit 33b611a.

Repository: https://github.com/llmware-ai/llmware

## Backend

### Data

- **[chromadb](https://seerepo.com/uses/chromadb)**
- **[pgvector](https://seerepo.com/uses/pgvector)**
- **[psycopg](https://seerepo.com/uses/psycopg)**
- **psycopg-binary**
- **[pymongo](https://seerepo.com/uses/pymongo)**
- **[Postgres](https://seerepo.com/uses/postgres)**: 3 files · [llmware/embeddings.py, line 2046](https://github.com/llmware-ai/llmware/blob/33b611adeb3378a474b69f12d303d1750babad41/llmware/embeddings.py#L2046)
- **[MongoDB](https://seerepo.com/uses/mongodb)**: 2 files · [llmware/resources.py, line 31](https://github.com/llmware-ai/llmware/blob/33b611adeb3378a474b69f12d303d1750babad41/llmware/resources.py#L31)
- **[pymilvus](https://seerepo.com/uses/pymilvus)**: 1 file

### AI

- **[einops](https://seerepo.com/uses/einops)**
- **[datasets](https://seerepo.com/uses/datasets)**: 9 files
- **[torch](https://seerepo.com/uses/torch)**: 7 files
- **[transformers](https://seerepo.com/uses/transformers)**: 7 files
- **[tokenizers](https://seerepo.com/uses/tokenizers)**: 2 files

### Services

- **[Hugging Face](https://seerepo.com/uses/hugging-face)**: 4 files · [llmware/models.py, line 383](https://github.com/llmware-ai/llmware/blob/33b611adeb3378a474b69f12d303d1750babad41/llmware/models.py#L383)
- **[OpenAI](https://seerepo.com/uses/openai)**: 2 files · [solutions/gguf/using-azure-openai.py, line 9](https://github.com/llmware-ai/llmware/blob/33b611adeb3378a474b69f12d303d1750babad41/solutions/gguf/using-azure-openai.py#L9)

## Support

### The base

- **[Streamlit](https://seerepo.com/uses/streamlit)**: 13 files

### Deploy

- **[boto3](https://seerepo.com/uses/boto3)**: 1 file

### Other

- **colorama**: 3 files
- **requests**: 3 files
- **NumPy**: 2 files
- **soundfile**: 1 file
- **soxr**: 1 file
- **yfinance**: 1 file

## Other repos with a similar stack

- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): chromadb, pgvector, psycopg, pymilvus, OpenAI, einops, datasets, torch, transformers, tokenizers, boto3 · [Compare](https://seerepo.com/compare/llmware-ai/llmware/vs/run-llama/llama_index)
- [open-webui/open-webui](https://seerepo.com/r/open-webui/open-webui/built): chromadb, pgvector, psycopg, Postgres, pymilvus, Hugging Face, OpenAI, einops, transformers, boto3 · [Compare](https://seerepo.com/compare/llmware-ai/llmware/vs/open-webui/open-webui)
- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/built): chromadb, Postgres, pymilvus, Hugging Face, OpenAI, Streamlit, datasets, torch, transformers, tokenizers · [Compare](https://seerepo.com/compare/datawhalechina/hello-agents/vs/llmware-ai/llmware)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): pymongo, MongoDB, Hugging Face, einops, datasets, torch, transformers, tokenizers, boto3 · [Compare](https://seerepo.com/compare/llmware-ai/llmware/vs/ray-project/ray)
- [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/built): Postgres, Hugging Face, OpenAI, einops, datasets, torch, transformers, tokenizers · [Compare](https://seerepo.com/compare/llmware-ai/llmware/vs/mudler/LocalAI)
- [agno-agi/agno](https://seerepo.com/r/agno-agi/agno/built): chromadb, pgvector, psycopg, psycopg-binary, Postgres, Hugging Face, OpenAI, tokenizers · [Compare](https://seerepo.com/compare/agno-agi/agno/vs/llmware-ai/llmware)

## Frequently asked questions

### What language is llmware written in?

llmware is written in Python, with 71,264 written lines.

### What framework does llmware use?

llmware is built with Streamlit.

### What database does llmware use?

llmware stores its data in Postgres and MongoDB.

The proof: [llmware/embeddings.py, line 2046](https://github.com/llmware-ai/llmware/blob/33b611adeb3378a474b69f12d303d1750babad41/llmware/embeddings.py#L2046)

### Does llmware use AI?

Yes. llmware uses AI through einops, datasets, torch, transformers, tokenizers, and OpenAI.

### What services does llmware use?

llmware uses chromadb, pgvector, psycopg, psycopg-binary, pymongo, pymilvus, and Hugging Face.

### Does llmware have tests?

Yes. llmware has 18 test files.

### Which repos have a stack like llmware's?

The ones that share most of its stack: run-llama/llama_index, open-webui/open-webui, and datawhalechina/hello-agents.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.