Source: https://seerepo.com/r/run-llama/llama_index/built
Markdown source: https://seerepo.com/r/run-llama/llama_index/built.md
Description: llama_index is a Python repo built with starlette, anyio, graphql-core, tornado, AIOHTTP, and 1 more.

# What is llama_index built with?

llama_index is a Python repo built with starlette, anyio, graphql-core, tornado, AIOHTTP, and 1 more. It stores its data in pyarrow, lancedb, oracledb, DuckDB, pymilvus, and 6 more, reaches it with SQLAlchemy, signs people in with argon2-cffi, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, and 3 more, uses AI through einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, and 37 more, makes its content with beautifulsoup4, bleach, markupsafe, mistune, nbformat, and 23 more, validates its data with jsonschema-specifications, marshmallow, referencing, rfc3339-validator, Pydantic, and 4 more, is tested with pytest-cov, Pytest, pytest-asyncio, playwright, pytest-mock, and 2 more, deploys with opentelemetry-api, opentelemetry-semantic-conventions, prometheus-client, psutil, python-json-logger, and 4 more, and uses aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, and 19 more. It has 473,236 written lines, with 1,607 test files.

Read on November 5, 2026, at commit 444fdf0.

Repository: https://github.com/run-llama/llama_index

## Frontend

### Styles

- **soupsieve**
- **tinycss2**

### Interface

- **ipywidgets**
- **matplotlib-inline**
- **[prompt-toolkit](https://seerepo.com/uses/prompt-toolkit)**
- **[matplotlib](https://seerepo.com/uses/matplotlib)**: 2 files
- **[Rich](https://seerepo.com/uses/rich)**: 2 files

## Backend

### The base

- **[starlette](https://seerepo.com/uses/starlette)**: 2 files

### Data

- **aiomysql**
- **[aiosqlite](https://seerepo.com/uses/aiosqlite)**
- **async-lru**
- **asyncpg**
- **azure-search-documents**
- **azure-storage-blob**
- **ibm-db**
- **pgvecto-rs**
- **pgvector**
- **[psycopg](https://seerepo.com/uses/psycopg)**
- **[psycopg2-binary](https://seerepo.com/uses/psycopg2-binary)**
- **pyzmq**
- **[redis](https://seerepo.com/uses/redis)**
- **weaviate-client**
- **[pyarrow](https://seerepo.com/uses/pyarrow)**: 5 files
- **lancedb**: 4 files
- **oracledb**: 4 files
- **DuckDB**: 3 files
- **pymilvus**: 3 files
- **[SQLite](https://seerepo.com/uses/sqlite)**: 3 files · [llama-index-core/pyproject.toml, line 82](https://github.com/run-llama/llama_index/blob/444fdf0684707de62ebb447d658dba137dd9cb99/llama-index-core/pyproject.toml#L82)
- **tablestore**: 3 files
- **[chromadb](https://seerepo.com/uses/chromadb)**: 2 files
- **falkordb**: 2 files
- **[MySQL](https://seerepo.com/uses/mysql)**: 2 files · [llama-index-integrations/vector_stores/llama-index-vector-stores-alibabacloud-mysql/pyproject.toml, line 40](https://github.com/run-llama/llama_index/blob/444fdf0684707de62ebb447d658dba137dd9cb99/llama-index-integrations/vector_stores/llama-index-vector-stores-alibabacloud-mysql/pyproject.toml#L40)
- **pinecone**: 2 files
- **clickhouse-connect**: 1 file
- **gcsfs**: 1 file
- **pyiceberg**: 1 file
- **pymochow**: 1 file
- **pymysql**: 1 file
- **pyobvector**: 1 file
- **s3fs**: 1 file
- **tcvectordb**: 1 file
- **typesense**: 1 file

### Data access

- **[SQLAlchemy](https://seerepo.com/uses/sqlalchemy)**: 28 files

### Sign-in

- **argon2-cffi**
- **[azure-identity](https://seerepo.com/uses/azure-identity)**
- **[Google](https://seerepo.com/uses/google)**
- **google-auth-httplib2**
- **google-auth-oauthlib**: 8 files
- **[cryptography](https://seerepo.com/uses/cryptography)**: 2 files
- **[pyjwt](https://seerepo.com/uses/pyjwt)**: 2 files
- **msal**: 1 file

### AI

- **[einops](https://seerepo.com/uses/einops)**
- **firecrawl-py**
- **guardrails-ai**
- **llama-index-core**
- **mem0ai**
- **[openai](https://seerepo.com/uses/openai)**
- **[opencv-python](https://seerepo.com/uses/opencv-python)**
- **PaddlePaddle**
- **tavily-python**
- **[torch](https://seerepo.com/uses/torch)**: 25 files
- **[transformers](https://seerepo.com/uses/transformers)**: 23 files
- **ibm-watsonx-ai**: 6 files
- **cohere**: 5 files
- **[LangChain](https://seerepo.com/uses/langchain)**: 5 files
- **[tiktoken](https://seerepo.com/uses/tiktoken)**: 5 files
- **[mcp](https://seerepo.com/uses/mcp)**: 4 files
- **sentence-transformers**: 4 files
- **dashscope**: 3 files
- **fastembed**: 3 files
- **flagembedding**: 3 files
- **nltk**: 3 files
- **[sentencepiece](https://seerepo.com/uses/sentencepiece)**: 3 files
- **[litellm](https://seerepo.com/uses/litellm)**: 2 files
- **ModelScope**: 2 files
- **[Ollama](https://seerepo.com/uses/ollama)**: 2 files
- **openvino**: 2 files
- **[scikit-learn](https://seerepo.com/uses/scikit-learn)**: 2 files
- **tritonclient**: 2 files
- **vLLM**: 2 files
- **[datasets](https://seerepo.com/uses/datasets)**: 1 file
- **exa-py**: 1 file
- **flashrank**: 1 file
- **hnswlib**: 1 file
- **langfuse**: 1 file
- **mlx**: 1 file
- **mlx-lm**: 1 file
- **nomic**: 1 file
- **optimum**: 1 file
- **paddleocr**: 1 file
- **[peft](https://seerepo.com/uses/peft)**: 1 file
- **presidio-analyzer**: 1 file
- **[tokenizers](https://seerepo.com/uses/tokenizers)**: 1 file

### Services

- **ElevenLabs**: 3 files · [llama-index-integrations/tools/llama-index-tools-elevenlabs/llama_index/tools/elevenlabs/base.py, line 34](https://github.com/run-llama/llama_index/blob/444fdf0684707de62ebb447d658dba137dd9cb99/llama-index-integrations/tools/llama-index-tools-elevenlabs/llama_index/tools/elevenlabs/base.py#L34)

## Support

### The base

- **[anyio](https://seerepo.com/uses/anyio)**
- **graphql-core**
- **tornado**
- **[AIOHTTP](https://seerepo.com/uses/aiohttp)**: 15 files
- **Ray**: 2 files

### Content

- **[beautifulsoup4](https://seerepo.com/uses/beautifulsoup4)**
- **bleach**
- **markupsafe**
- **mistune**
- **nbformat**
- **newspaper3k**
- **xlrd**
- **[pillow](https://seerepo.com/uses/pillow)**: 22 files
- **bs4**: 17 files
- **html2text**: 6 files
- **unstructured**: 6 files
- **[defusedxml](https://seerepo.com/uses/defusedxml)**: 4 files
- **[jinja2](https://seerepo.com/uses/jinja2)**: 4 files
- **[lxml](https://seerepo.com/uses/lxml)**: 4 files
- **[pymupdf](https://seerepo.com/uses/pymupdf)**: 4 files
- **filetype**: 3 files
- **docx2txt**: 2 files
- **markdownify**: 2 files
- **docling**: 1 file
- **lxml-html-clean**: 1 file
- **markitdown**: 1 file
- **nbconvert**: 1 file
- **pdf2image**: 1 file
- **pdfplumber**: 1 file
- **[pypdf](https://seerepo.com/uses/pypdf)**: 1 file
- **pypdf2**: 1 file
- **tinytag**: 1 file
- **youtube-transcript-api**: 1 file

### Validation

- **jsonschema-specifications**
- **marshmallow**
- **referencing**
- **rfc3339-validator**
- **[Pydantic](https://seerepo.com/uses/pydantic)**: 70 files
- **docling-core**: 2 files
- **annotated-types**: 1 file
- **[jsonschema](https://seerepo.com/uses/jsonschema)**: 1 file
- **pydantic-core**: 1 file

### Testing

- **pytest-cov**
- **Pytest**: 474 files
- **pytest-asyncio**: 53 files
- **playwright**: 7 files
- **pytest-mock**: 6 files
- **Faker**: 2 files
- **Selenium**: 2 files

### Deploy

- **opentelemetry-api**
- **opentelemetry-semantic-conventions**
- **prometheus-client**
- **[psutil](https://seerepo.com/uses/psutil)**
- **python-json-logger**
- **[boto3](https://seerepo.com/uses/boto3)**: 16 files
- **[docker](https://seerepo.com/uses/docker)**: 7 files
- **Alibaba Cloud**: 6 files
- **[OpenTelemetry](https://seerepo.com/uses/opentelemetry)**: 2 files

### Tools

- **astroid**
- **asttokens**
- **Black**
- **boto3-stubs**
- **cfgv**
- **codespell**
- **coverage**
- **distlib**
- **executing**
- **griffe**
- **identify**
- **iniconfig**
- **ipykernel**
- **jedi**
- **Jupyter**
- **jupyterlab**
- **mccabe**
- **mypy**
- **mypy-extensions**
- **nbclient**
- **nodeenv**
- **notebook**
- **overrides**
- **parso**
- **pathspec**
- **pip**
- **pluggy**
- **pre-commit**
- **pure-eval**
- **pycparser**
- **pygments**
- **pylint**
- **Ruff**
- **stack-data**
- **types-protobuf**
- **types-python-dateutil**
- **types-pyyaml**
- **types-requests**
- **types-setuptools**
- **virtualenv**
- **typing-extensions**: 39 files
- **click**: 9 files
- **packaging**: 8 files
- **ipython**: 3 files
- **Setuptools**: 1 file

### Other

- **ag-ui-protocol**
- **aiohappyeyeballs**
- **aiohttp-retry**
- **aiosignal**
- **arrow**
- **async-timeout**
- **attrs**
- **Babel**
- **certifi**
- **cffi**
- **chardet**
- **charset-normalizer**
- **colorama**
- **comm**
- **decorator**
- **dill**
- **exceptiongroup**
- **filelock**
- **frozenlist**
- **google-api-core**
- **greenlet**
- **h11**
- **httpcore**
- **idna**
- **importlib-metadata**
- **joblib**
- **json5**
- **jsonpointer**
- **multidict**
- **pexpect**
- **propcache**
- **ptyprocess**
- **python-gitlab**
- **pywin32**
- **regex**
- **requests-toolbelt**
- **rpds-py**
- **sniffio**
- **sseclient-py**
- **tomlkit**
- **traitlets**
- **typing-inspection**
- **wcwidth**
- **webcolors**
- **websocket-client**
- **zipp**
- **requests**: 123 files
- **httpx**: 53 files
- **fsspec**: 36 files
- **NumPy**: 36 files
- **tenacity**: 32 files
- **pandas**: 25 files
- **deprecated**: 18 files
- **tqdm**: 14 files
- **dataclasses-json**: 9 files
- **pyyaml**: 6 files
- **nest-asyncio**: 5 files
- **arxiv**: 3 files
- **websockets**: 3 files
- **networkx**: 2 files
- **pyaudio**: 2 files
- **tomli**: 2 files
- **wikipedia**: 2 files
- **yfinance**: 2 files
- **dirtyjson**: 1 file
- **duckduckgo-search**: 1 file
- **geopy**: 1 file
- **grpcio**: 1 file
- **more-itertools**: 1 file
- **platformdirs**: 1 file
- **Polars**: 1 file
- **praw**: 1 file
- **python-dateutil**: 1 file
- **python-dotenv**: 1 file
- **retrying**: 1 file
- **six**: 1 file
- **slack-sdk**: 1 file
- **termcolor**: 1 file
- **trafilatura**: 1 file
- **tweepy**: 1 file
- **urllib3**: 1 file
- **wandb**: 1 file
- **wrapt**: 1 file
- **yarl**: 1 file

## Other repos with a similar stack

- [apache/superset](https://seerepo.com/r/apache/superset/built): starlette, psycopg2-binary, pyzmq, Redis, pyarrow, oracledb, MySQL, clickhouse-connect, pymysql, anyio, AIOHTTP, soupsieve, tinycss2, ipywidgets, matplotlib-inline, prompt-toolkit, matplotlib, Rich, SQLAlchemy, argon2-cffi, Google, google-auth-oauthlib, cryptography, pyjwt, tiktoken, MCP, beautifulsoup4, bleach, markupsafe, xlrd, pillow, defusedxml, jinja2, jsonschema-specifications, referencing, rfc3339-validator, Pydantic, annotated-types, jsonschema, pydantic-core, prometheus-client, psutil, python-json-logger, boto3, docker, OpenTelemetry · [Compare](https://seerepo.com/compare/apache/superset/vs/run-llama/llama_index)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): azure-search-documents, azure-storage-blob, psycopg2-binary, pyarrow, chromadb, anyio, AIOHTTP, matplotlib, Rich, Google, google-auth-httplib2, google-auth-oauthlib, mem0ai, OpenAI, opencv-python, torch, transformers, tiktoken, MCP, sentence-transformers, nltk, sentencepiece, litellm, Ollama, scikit-learn, vLLM, datasets, peft, beautifulsoup4, xlrd, pillow, html2text, lxml, pymupdf, pdfplumber, pypdf, pypdf2, youtube-transcript-api, Pydantic, psutil · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/run-llama/llama_index)
- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/built): starlette, aiosqlite, asyncpg, psycopg2-binary, Redis, oracledb, pymilvus, SQLite, chromadb, anyio, AIOHTTP, matplotlib, Rich, SQLAlchemy, OpenAI, tavily-python, torch, transformers, tiktoken, MCP, sentence-transformers, scikit-learn, datasets, peft, tokenizers, beautifulsoup4, xlrd, pillow, jinja2, lxml, pymupdf, pdfplumber, pypdf, Pydantic, annotated-types, jsonschema, pydantic-core, OpenTelemetry · [Compare](https://seerepo.com/compare/datawhalechina/hello-agents/vs/run-llama/llama_index)
- [Significant-Gravitas/AutoGPT](https://seerepo.com/r/Significant-Gravitas/AutoGPT/built): psycopg2-binary, Redis, pyarrow, falkordb, pinecone, pymysql, ElevenLabs, AIOHTTP, prompt-toolkit, Rich, SQLAlchemy, Google, google-auth-oauthlib, cryptography, pyjwt, firecrawl-py, mem0ai, OpenAI, tavily-python, tiktoken, Ollama, exa-py, langfuse, beautifulsoup4, bleach, pillow, html2text, jinja2, pypdf, youtube-transcript-api, Pydantic, jsonschema, prometheus-client, psutil, boto3, docker · [Compare](https://seerepo.com/compare/run-llama/llama_index/vs/Significant-Gravitas/AutoGPT)
- [open-webui/open-webui](https://seerepo.com/r/open-webui/open-webui/built): pgvector, psycopg2-binary, Redis, weaviate-client, pyarrow, oracledb, pymilvus, SQLite, chromadb, pinecone, pymysql, AIOHTTP, SQLAlchemy, azure-identity, cryptography, pyjwt, OpenAI, tiktoken, MCP, beautifulsoup4, xlrd, pillow, lxml, pypdf, youtube-transcript-api, Pydantic, psutil, boto3 · [Compare](https://seerepo.com/compare/open-webui/open-webui/vs/run-llama/llama_index)
- [vllm-project/vllm](https://seerepo.com/r/vllm-project/vllm/built): starlette, pyzmq, AIOHTTP, Ray, einops, OpenAI, torch, transformers, tiktoken, MCP, sentencepiece, datasets, peft, tokenizers, markupsafe, pillow, jinja2, Pydantic, jsonschema, pydantic-core, opentelemetry-api, prometheus-client, psutil, python-json-logger, OpenTelemetry · [Compare](https://seerepo.com/compare/run-llama/llama_index/vs/vllm-project/vllm)

## Frequently asked questions

### What language is llama_index written in?

llama_index is written in Python, with 473,236 written lines.

### What framework does llama_index use?

llama_index is built with starlette, anyio, graphql-core, tornado, AIOHTTP, and Ray.

### What database does llama_index use?

llama_index stores its data in pyarrow, lancedb, oracledb, DuckDB, pymilvus, SQLite, tablestore, chromadb, falkordb, MySQL, and pinecone and reaches it with SQLAlchemy.

### What does llama_index sign people in with?

llama_index signs people in with argon2-cffi, azure-identity, Google, google-auth-httplib2, google-auth-oauthlib, cryptography, pyjwt, and msal.

### Does llama_index use AI?

Yes. llama_index uses AI through einops, firecrawl-py, guardrails-ai, llama-index-core, mem0ai, openai, opencv-python, PaddlePaddle, tavily-python, torch, transformers, ibm-watsonx-ai, cohere, LangChain, tiktoken, mcp, sentence-transformers, dashscope, fastembed, flagembedding, nltk, sentencepiece, litellm, ModelScope, Ollama, openvino, scikit-learn, tritonclient, vLLM, datasets, exa-py, flashrank, hnswlib, langfuse, mlx, mlx-lm, nomic, optimum, paddleocr, peft, presidio-analyzer, and tokenizers.

### What services does llama_index use?

llama_index uses aiomysql, aiosqlite, async-lru, asyncpg, azure-search-documents, azure-storage-blob, ibm-db, pgvecto-rs, pgvector, psycopg, psycopg2-binary, pyzmq, redis, weaviate-client, clickhouse-connect, gcsfs, pyiceberg, pymochow, pymysql, pyobvector, s3fs, tcvectordb, typesense, and ElevenLabs.

### Does llama_index have tests?

Yes. llama_index has 1,607 test files and is tested with pytest-cov, Pytest, pytest-asyncio, playwright, pytest-mock, Faker, and Selenium.

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

The ones that share most of its stack: apache/superset, bojieli/ai-agent-book, 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.