Read 2026-10-22
run-llama/llama_index: technical due diligence, read from its repository
What Borehole read in run-llama/llama_index's code and history at 619d746: its licence, security advisories, releases, review practice, tests, dependencies and operations. Every finding cites the file and line it rests on. The full report also covers the team and asks the questions the code cannot answer.
| Dimension | Rating |
|---|---|
| Architecture & Codebase — including AI provenance | strong |
| Engineering Process & SDLC Maturity | strong |
| Product & Engineering Maturity | adequate |
| Security & Reliability Posture | adequate |
| Observability & Operations | adequate |
| Fit with the Acquirer | not assessable |
Architecture & Codebase — including AI provenance
strongNo finding.
Engineering Process & SDLC Maturity
strongNo finding.
Product & Engineering Maturity
adequateEffort is shifting from building to rewriting
adequateDeleted lines per line added rose from 0.29 to 0.76 between the first and second halves of this history. Rework is normal and often healthy, but a rising ratio means an increasing share of the team's time is spent replacing code that already exists rather than building what does not. Whether that is deliberate repayment or churn is a question for the team.
| first half 0.29, second half 0.76 (split 2024-10-23) |
Fixes are 54% of recent work, up from 33%
adequateIn the last two quarters 54% of commits were fixes, against 33% in the quarters before. Rising fix work usually means quality debt is coming due, and it takes time that new work would have had.
| 52%, 56%, 45%, 33%, 30%, 30%, 32%, 29% |
17 files still carry code deprecated more than two years ago
adequate17 files were marked deprecated over two years ago and still are, the oldest since Feb 2024. A deprecation is a promise to remove. Ask what still depends on these, and whether removing them is scheduled.
llama-index-core/llama_index/core/schema.py — deprecated since Feb 2024 |
llama-index-core/llama_index/core/evaluation/dataset_generation.py — deprecated since Feb 2024 |
llama-index-core/llama_index/core/vector_stores/types.py — deprecated since Feb 2024 |
llama-index-integrations/embeddings/llama-index-embeddings-bedrock/llama_index/embeddings/bedrock/base.py — deprecated since Feb 2024 |
llama-index-integrations/llms/llama-index-llms-localai/llama_index/llms/localai/base.py — deprecated since Feb 2024 |
Security & Reliability Posture
adequate38 locked dependencies have published vulnerabilities, 64 high or critical in what ships
adequate38 of 778 locked dependencies match 157 published advisories in OSV, 86 of them rated high or critical. A lockfile says which version is installed, not whether the flawed code is reachable from this product, so each needs a look. Most are fixed by an upgrade, and the advisory names the version.
llama-index-core/uv.lock — certifi 2026.7.22: GHSA-6q48-6c7w-9gw2 (critical), fixed in 2026.10.19 |
llama-index-integrations/embeddings/llama-index-embeddings-autoembeddings/uv.lock — chromadb 1.5.9: GHSA-36p7-vc44-83pf (critical) |
llama-index-core/uv.lock — pillow 12.3.0: GHSA-332p-7hrc-92wf (critical), fixed in 13.0.0 |
8 advisories against this project in the last 24 months, 5 high or critical
adequateThe newest was published on 2026-02-02. A project that publishes advisories is telling its users about its fixes, and the count and pace say how much security work it carries. Whether 1 of them are fixed in the code you ship could not be told from this history: its version is only known to be at least 0.14.25. Answer lives in: the release you run, set against each fixed version.
| 2026-02-02: GHSA-488g-hw5f-x29p (moderate), fixed in 0.12.41: llama-index-core vulnerable to Uncontrolled Resource Consumption |
| 2026-01-12: CVE-2024-14021 (high): LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_i |
| 2025-09-27: GHSA-cr7q-2w66-hjcm (high), fixed in 0.13.0: llama-index-core insecurely handles temporary files |
| 2025-08-26: GHSA-7753-xrfw-ch36 (high), fixed in 0.12.38: LlamaIndex affected by a Denial of Service (DOS) in JSONReader |
| 2025-07-07: GHSA-2rhq-96q8-4vjq (high), fixed in 0.12.41: LlamaIndex vulnerable to Path Traversal attack through its encode_image function |
Observability & Operations
adequateNo structured logging library is in use
adequateNothing references a structured logging library. Logs that are written to be read by a person are not searchable by a machine, which means incident response here is proportional to how well someone remembers the codebase rather than to what the tooling can find.
| searched 331 files for 10 structured logging libraries; 0 matched |
One request cannot be followed through the logs
adequateNothing in the service carries a request or correlation id, and there is no tracing. When a customer reports a failure, the log lines that belong to their request cannot be picked out from everyone else's.
| no request id, correlation id or tracing found |
No error reporter is wired in
adequateNothing in the service initialises an error reporter (Sentry, Rollbar, Bugsnag, Honeybadger or an APM agent). An exception in production reaches a person only if someone is reading the logs, which usually means a customer reports it first.
| no error reporter initialised |
Fit with the Acquirer
not assessableNot rated: structurally not assessable from a repository.
Read more, or read your own
The full report on run-llama/llama_index: every dimension, the questions for the room, and the audit log.
Survey a repository: free on public repositories. Private code is read on your own machine by a collector whose source you can read first.