TraceLite
Lightweight LLM observability SDK with vector semantic caching using PostgreSQL (pgvector) and Redis.
Features
- Async Telemetry: Logs token usage, cost, latency, and TTFT in background threads.
- Two-Tier Caching: Exact hash caching (Redis) + Semantic vector caching (pgvector).
- Fallback Token Counting: Uses
tiktokenif native usage streaming metadata is omitted.
Installation
pip install tracelite
from tracelite.client import ObservedOpenAI
client = ObservedOpenAI(
api_key="your-openai-api-key",
db_url="postgresql://tracelite:secretpassword@localhost:5432/llm_observability"
)
response = client.chat_completion(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello world!"}]
)
print(response.choices[0].message.content)
---
### 2. Bump version in `pyproject.toml`
Change the version string to **`0.1.8`**:
```toml
version = "0.1.8"
1 maintainer
Release files for tracelite 0.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| tracelite-0.1.8.tar.gz | 6.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tracelite-0.1.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 14.7 kB
Release files / tracelite-0.1.8.tar.gz
| Download URL | tracelite-0.1.8.tar.gz |
|---|---|
| Size | 6.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d49fea1ea8ac063cffeb29fc4d613dd5df4482b3fffdb94d7b7656297f2ea47c
|
|
BLAKE2b-256 checksum How to use checksums |
77501f3ed2eb283308097d6df1f205c563a7e2cf6cb914226bd6161178d02ea0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 25, 2026.
Transparency logRelease files / tracelite-0.1.8-py3-none-any.whl
| Download URL | tracelite-0.1.8-py3-none-any.whl |
|---|---|
| Size | 7.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
102519e8cbc30bd2c0f6ba6c469ca749d66d11a4221369df2cb9a6f513e2f920
|
|
BLAKE2b-256 checksum How to use checksums |
ce0ff2f8eff3a55d71cf7da8ed4d492e8e176f67dba6571e2f17e955f809610f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 25, 2026.
Transparency log
