SQLAgent Community
SQLAgent Community is a Python library for creating intelligent agents that can query SQLite databases using LLMs, generate SQL from natural language, and maintain conversation memory. Ideal for exploratory data analysis, conversational dashboards, or automating complex queries.
Requirements
- Python >= 3.10
- SQLite
- Ollama installed and configured
- Ollama provides the LLM and embedding models used by SQLAgent
- Pandas (for reading Excel files)
- Rich (optional, for nice logs)
Installation
You can install via pip (once published on PyPI):
pip install sqlagent-community
Configuration
Suggested file structure
dataset/
├─ data.db # SQLite database
├─ excels/ # Excel files to build the DB
vector_db/
├─ schema_embeddings.pkl # Schema embeddings
context/
├─ file.md # Additional context for the agent
Initialize Builder and database
from sqlagent_community.Builder import SQLBuilder
builder = SQLBuilder(
excel_dir="dataset/excels",
db_file="dataset/data.db",
embed_file="vector_db/schema_embeddings.pkl",
embed_model="qwen3-embedding:0.6b",
verbose=True
)
builder.build()
Set up Chat and Memory
from sqlagent_community.memory.ChatManager import ChatManager
from sqlagent_community.memory.ConversationSummaryBufferMemory import ConversationSummaryBufferMemory
manager = ChatManager()
chat_id = manager.create_chat()
memory = ConversationSummaryBufferMemory(chat_id=chat_id)
Initialize the Agent
from sqlagent_community.Agent import SQLAgent
agent = SQLAgent(
db_path="dataset/data.db",
embed_file="vector_db/schema_embeddings.pkl",
embedding_model="qwen3-embedding:0.6b",
llm_model="qwen2.5:7b",
text2sql="qwen2.5-coder:7b",
memory=memory,
context="./context/file.md",
verbose=True
)
Asking questions to the agent
question = "What is the average altitude per municipality of the collections?"
result = agent.run(question)
print(result)
The agent converts the question into SQL, executes it on the database, and returns the result, while maintaining conversation history and context.
Features
- Automatic SQLite database construction from Excel files.
- SQL generation via LLM from natural language.
- Summarized conversational memory per chat.
- Additional context from Markdown files.
- Detailed logs for debugging.
License
MIT License – see the LICENSE file for details.
Metadata
Release files for sqlagent-community 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| sqlagent_community-0.1.3.tar.gz | 16.2 kB | Without provenance | Details for sqlagent_community-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sqlagent_community-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for sqlagent_community-0.1.3-py3-none-any.whl |
Total release size: 36.5 kB
Release files / sqlagent_community-0.1.3.tar.gz
| Download URL | sqlagent_community-0.1.3.tar.gz |
|---|---|
| Size | 16.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
74ac91fa3483897a915bc90ff54198c1f662e3e07c5ab007760c96a653738f2c
|
|
BLAKE2b-256 checksum How to use checksums |
41d567c0b6400bc4034482d094f521e937939351b6d2e59654373645cd993b19
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / sqlagent_community-0.1.3-py3-none-any.whl
| Download URL | sqlagent_community-0.1.3-py3-none-any.whl |
|---|---|
| Size | 20.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e8a3354c4d32b4d73cd72b1579df7eb1e91ed036b1ae7e6ee11b606372afed1d
|
|
BLAKE2b-256 checksum How to use checksums |
4e1e595028291568c7ce0255bf7ce811d7eddd36a7e19fdf5cde9bf9184bb692
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for sqlagent-community 0.1.3
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.