Source: https://seerepo.com/compare/bojieli/ai-infra-book/vs/run-llama/llama_index
Markdown source: https://seerepo.com/compare/bojieli/ai-infra-book/vs/run-llama/llama_index.md
Description: ai-infra-book and llama_index share 51 technologies: pyarrow, Redis, s3fs, pyzmq, anyio, graphql-core, jupyter-core, starlette, tornado, Ray, AIOHTTP, matplotlib-inline, prompt-toolkit, matplotlib, SQLAlchemy, cryptography, Google, MCP, mlx, mlx-lm, nltk, open-clip-torch, OpenAI, peft, scikit-learn, sentencepiece, tiktoken, torch, transformers, einops, datasets, ModelScope, tokenizers, defusedxml, lxml, markupsafe, nbformat, pillow, pymupdf, jinja2, annotated-types, fastjsonschema, jsonschema, jsonschema-specifications, referencing, Pydantic, boto3, OpenTelemetry, opentelemetry-semantic-conventions, psutil, and prometheus-client. Both are written in Python.

# ai-infra-book vs llama_index

ai-infra-book and llama_index share 51 technologies: pyarrow, Redis, s3fs, pyzmq, anyio, graphql-core, jupyter-core, starlette, tornado, Ray, AIOHTTP, matplotlib-inline, prompt-toolkit, matplotlib, SQLAlchemy, cryptography, Google, MCP, mlx, mlx-lm, nltk, open-clip-torch, OpenAI, peft, scikit-learn, sentencepiece, tiktoken, torch, transformers, einops, datasets, ModelScope, tokenizers, defusedxml, lxml, markupsafe, nbformat, pillow, pymupdf, jinja2, annotated-types, fastjsonschema, jsonschema, jsonschema-specifications, referencing, Pydantic, boto3, OpenTelemetry, opentelemetry-semantic-conventions, psutil, and prometheus-client. Both are written in Python.

- [bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book): 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index): LlamaIndex is the document processing platform for AI

## What they share and what sets them apart

- In common: pyarrow, Redis, s3fs, pyzmq, anyio, graphql-core, jupyter-core, starlette, tornado, Ray, AIOHTTP, matplotlib-inline, prompt-toolkit, matplotlib, SQLAlchemy, cryptography, Google, MCP, mlx, mlx-lm, nltk, open-clip-torch, OpenAI, peft, scikit-learn, sentencepiece, tiktoken, torch, transformers, einops, datasets, ModelScope, tokenizers, defusedxml, lxml, markupsafe, nbformat, pillow, pymupdf, jinja2, annotated-types, fastjsonschema, jsonschema, jsonschema-specifications, referencing, Pydantic, boto3, OpenTelemetry, opentelemetry-semantic-conventions, psutil, prometheus-client
- Only in ai-infra-book: FastAPI, blobfile, gitdb, huey, s3transfer, smart-open, tensorboard-data-server, transferqueue, Hugging Face, Anthropic, Flask, flask-cors, graphene, graphql-relay, hypercorn, kui, Lightning, quart, uvicorn, werkzeug, cycler, mkdocs-material, fonttools, blessed, contourpy, Gradio, kaleido, Plotly, pyecharts, seaborn, alembic, itsdangerous, accelerate, apache-tvm-ffi, comet-ml, cuda-core, cuda-python, cuda-toolkit, cupy-cuda13x, decord2, descript-audio-codec, e2b, einx, emerging-optimizers, evaluate, fla-core, flash-linear-attention, flashinfer-cubin, flashinfer-python, jaxlib, llvmlite, loralib, mamba-ssm, math-verify, megatron-bridge, mistral-common, ml-dtypes, MLflow, mooncake-transfer-engine-cuda13, nixl, nvidia-cublas, nvidia-cudnn-cu12, nvidia-cudnn-cu13, nvidia-cudnn-frontend, nvidia-cufft, nvidia-cusolver, nvidia-cusparse, nvshmem4py-cu13, onnx-ir, onnxscript, openai-agents, opt-einsum, pythainlp, qwen-vl-utils, rouge-score, sacrebleu, sglang-router, silero-vad, sklearn-crfsuite, skops, spaCy, spacy-legacy, stanza, thinc, timm, torch-c-dlpack-ext, torchvision, tensordict, triton, safetensors, flash-attn, megatron-core, xformers, ONNX, deepspeed, diffusers, jax, librosa, torchaudio, causal-conv1d, cuda-bindings, nvidia-cuda-runtime, torchdata, transformer-engine, cairosvg, imageio, imageio-ffmpeg, mako, markdown-it-py, mdurl, pylatexenc, pytablewriter, python-magic, markdown, av, dacite, pathvalidate, typepy, msgspec, aiobotocore, botocore, colorlog, docker, gpustat, Gunicorn, opencensus-context, opentelemetry-exporter-prometheus, spacy-loggers, swanlab, loguru
- Only in llama_index: aiomysql, aiosqlite, async-lru, asyncpg, azure-cosmos, azure-data-tables, azure-search-documents, azure-storage-blob, ibm-db, llama-index-graph-stores-neo4j, llama-index-kvstore-couchbase, llama-index-storage-kv-store-azurecosmosnosql, llama-index-storage-kvstore-azure, llama-index-storage-kvstore-duckdb, llama-index-storage-kvstore-dynamodb, llama-index-storage-kvstore-elasticsearch, llama-index-storage-kvstore-firestore, llama-index-storage-kvstore-gel, llama-index-storage-kvstore-mongodb, llama-index-storage-kvstore-postgres, llama-index-storage-kvstore-redis, llama-index-storage-kvstore-tablestore, llama-index-vector-stores-duckdb, llama-index-vector-stores-postgres, nebula3-python, oss2, pgml, pgvecto-rs, pgvector, pickleshare, psycopg, psycopg2-binary, psycopg2-yugabytedb, pyathena, pydrive, pykx, pylance, pymongo, python-arango, pyvespa, redisvl, snowflake-sqlalchemy, tantivy, vearch, weaviate-client, Neo4j, aioboto3, lancedb, oracledb, DuckDB, gel, pymilvus, pysolr, SQLite, tablestore, aiosolr, aperturedb, astrapy, cassio, chromadb, dashvector, deeplake, falkordb, jaguardb-http-client, MySQL, pinecone, clickhouse-connect, couchdb3, gcsfs, hologres-vector, kdbai-client, objectbox, opendal, opengauss-sqlalchemy, pyairtable, pyepsilla, pyiceberg, pymochow, pymysql, pyobvector, rockset, singlestoredb, tair, tcvectordb, timescale-vector, typesense, vearch-cluster, vecs, vecx, ElevenLabs, jupyterlab-server, jupyterlab-pygments, soupsieve, tinycss2, ipywidgets, jupyter-server-terminals, jupyterlab-widgets, widgetsnbextension, Rich, sqlalchemy-yugabytedb, argon2-cffi, argon2-cffi-bindings, azure-identity, google-auth-httplib2, google-auth-oauthlib, pyjwt, msal, argilla, azure-ai-agents, azure-ai-inference, azure-ai-projects, contextual-client, diff-cover, firecrawl-py, friendli-client, guardrails-ai, llama-cpp-python, llama-index-core, llama-index-embeddings-dashscope, llama-index-embeddings-huggingface, llama-index-embeddings-openai, llama-index-embeddings-vertex, llama-index-indices-managed-vectara, llama-index-llms-anthropic, llama-index-llms-azure-openai, llama-index-llms-huggingface, llama-index-llms-llama-cpp, llama-index-llms-openai, llama-index-llms-openai-like, llama-index-node-parser-dashscope, llama-index-program-guidance, llama-index-readers-box, llama-index-readers-dashscope, llama-index-readers-database, llama-index-readers-remote, llama-index-readers-slack, llama-index-readers-upstage, llama-index-readers-web, llama-index-response-synthesizers-google, llama-index-tools-graphql, llama-index-tools-mcp, llama-index-tools-openapi, llama-index-utils-azure, llama-index-utils-huggingface, llama-index-utils-qianfan, llama-index-vector-stores-google, llama-index-workflows, mem0ai, ms-swift, opencv-python, openinference-instrumentation-llama-index, openvino-tokenizers, PaddlePaddle, portkey-ai, reka-api, signnow-mcp-server, tavily-python, typecast-python, llama-index-instrumentation, ibm-watsonx-ai, cohere, LangChain, bedrock-agentcore, sentence-transformers, dashscope, docarray, fastembed, flagembedding, llama-cloud, optimum-intel, ai21, aleph-alpha-client, chonkie, gigachat, guidance, hive-intelligence, igptai, konko, litellm, mixedbread, octoai, Ollama, openvino, openvino-genai, premai, tritonclient, valyu, vLLM, voyageai, wordlift-client, zep-python, zhipuai, agent-search, agentql, aimon, argilla-llama-index, assemblyai, bm25s, browserbase, cleanlab-tlm, cognee, colpali-engine, exa-py, flashrank, hnswlib, honeyhive, inferedge-moss, instructorembedding, isaacus, langfuse, llmlingua, llmsherpa, marvin, metaphor-python, moorcheh-sdk, multion, nomic, notdiamond, optimum, optimum-habana, paddleocr, presidio-analyzer, presidio-anonymizer, promptlayer, psychicapi, pydi-client, rank-llm, seltz, span-marker, superlinked, uptrain, vectorize-client, videodb, waii-sdk-py, beautifulsoup4, bleach, camelot-py, ghostscript, llama-index-readers-file, llama-index-readers-notion, llama-index-readers-youtube-transcript, maincontentextractor, marker-pdf, mistune, newspaper3k, nougat-ocr, pandocfilters, webencodings, xlrd, bs4, html2text, unstructured, filetype, bagel, docx2txt, markdownify, olefile, pypdf, pytesseract, dgml-utils, docling, layoutir, llama-parse, lxml-html-clean, markitdown, nbconvert, pdf2image, pdfplumber, striprtf, svglib, tika, tinytag, youtube-transcript-api, fqdn, marshmallow, rfc3339-validator, rfc3986-validator, rfc3987-syntax, docling-core, python-json-logger, Alibaba Cloud, oci

## Side by side

| | ai-infra-book | llama_index |
|---|---|---|
| Size | 1,438,355 lines written, 1,748 code files | 473,292 lines written, 2,055 code files |
| Who writes it | 16.6% of its commits signed by AI. With Claude Code and Codex | 0.2% of its commits signed by AI. With Claude Code, Cursor, and GitHub Copilot |
| Activity | Last push October 1, 2026, 314 commits, 8,032 stars | Last push November 14, 2026, 7,971 commits, 52,930 stars |
| Tests | 1,093 test files. 17.8% of its code files have a test that imports them | 1,607 test files. 46.5% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, ai-infra-book or llama_index?

ai-infra-book, with 1,438,355 lines written; llama_index has 473,292.

The proof: [bojieli/ai-infra-book's code at commit 3bdcb4f](https://github.com/bojieli/ai-infra-book/tree/3bdcb4fcab73010eeaccf31cc10a8242a895d82e)

### Which has more GitHub stars, ai-infra-book or llama_index?

llama_index, with 52,930 stars; ai-infra-book has 8,032.

The proof: [run-llama/llama_index on GitHub](https://github.com/run-llama/llama_index)

### Which has more tests, ai-infra-book or llama_index?

llama_index, with 1,607 test files; ai-infra-book has 1,093.

The proof: [run-llama/llama_index's code at commit 99d7433](https://github.com/run-llama/llama_index/tree/99d7433f6f71888951379ccca9294e272442c832)

### Which was updated more recently, ai-infra-book or llama_index?

llama_index: its last push was on November 14, 2026, and ai-infra-book's on October 1, 2026.

The proof: [run-llama/llama_index's commits on GitHub](https://github.com/run-llama/llama_index/commits)

### Which has more commits signed by AI, ai-infra-book or llama_index?

ai-infra-book: an AI signed 16.6% of its commits, with Claude Code and Codex; in llama_index, 0.2%.

The proof: [the commits each tool signed in bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book/ai)

## Sources

- bojieli/ai-infra-book: Read on November 17, 2026, at commit 3bdcb4f (https://github.com/bojieli/ai-infra-book/tree/3bdcb4fcab73010eeaccf31cc10a8242a895d82e)
- run-llama/llama_index: Read on November 18, 2026, at commit 99d7433 (https://github.com/run-llama/llama_index/tree/99d7433f6f71888951379ccca9294e272442c832)

## 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.
