No project description provided
Project description
chatbot
This is a hands-on project to learn to create chatbot agent using LangChain & LangGraph. Use hatch package manager
Based on gpt-4o-mini LLM model, with added features:
- Tool calling: multiply tool, web search tool
- Memory: short term memory from conversation thread
- Human-in-the-loop: verify tool call before executing, in case conversational topic is sensitive
- State: add custom state "sensitivity", indicating if conversation topic is sensitive or not
Agent architecture: use 2 chat models for separation of concern
- Helper model to classify if conversation is sensitive or not
- Main model equiped with tools
Added minimal unit tests
Prepared for deployment as standalone container via LangGraph Platform
Table of Contents
Installation
PyPI package: https://pypi.org/project/chatbot_nam685/
pip install chatbot_nam685
License
chatbot_nam685 is distributed under the terms of the MIT license.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file chatbot_nam685-0.0.9.tar.gz.
File metadata
- Download URL: chatbot_nam685-0.0.9.tar.gz
- Upload date:
- Size: 94.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
73475e6a25fed06bfd037809ef64795a7b7f8f5c5406810ef6b7ea473e7cf70a
|
|
| MD5 |
0df62d2b9774030228e584dc40df819f
|
|
| BLAKE2b-256 |
17415d904cc883ec0016989d2e357192c986b3228b32126865453edd2e948d4f
|
Provenance
The following attestation bundles were made for chatbot_nam685-0.0.9.tar.gz:
Publisher:
github_cd.yaml on nam685/chatbot
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
chatbot_nam685-0.0.9.tar.gz -
Subject digest:
73475e6a25fed06bfd037809ef64795a7b7f8f5c5406810ef6b7ea473e7cf70a - Sigstore transparency entry: 245641894
- Sigstore integration time:
-
Permalink:
nam685/chatbot@8c12676ed47ea16c4f3223524ab02ffd08bcfe08 -
Branch / Tag:
refs/tags/v1.0.0 - Owner: https://github.com/nam685
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
github_cd.yaml@8c12676ed47ea16c4f3223524ab02ffd08bcfe08 -
Trigger Event:
release
-
Statement type:
File details
Details for the file chatbot_nam685-0.0.9-py3-none-any.whl.
File metadata
- Download URL: chatbot_nam685-0.0.9-py3-none-any.whl
- Upload date:
- Size: 7.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6bf09c9e34f253f6a6a2d153afe1a2d95bf4dd566f84ec9114ac03dab98f126d
|
|
| MD5 |
31176a6654ac5cb70d5e483d70ae9194
|
|
| BLAKE2b-256 |
e2446a644fcff1943cd37e66bc5e3cc94eab8121a943f032b15e8be560dddd51
|
Provenance
The following attestation bundles were made for chatbot_nam685-0.0.9-py3-none-any.whl:
Publisher:
github_cd.yaml on nam685/chatbot
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
chatbot_nam685-0.0.9-py3-none-any.whl -
Subject digest:
6bf09c9e34f253f6a6a2d153afe1a2d95bf4dd566f84ec9114ac03dab98f126d - Sigstore transparency entry: 245641895
- Sigstore integration time:
-
Permalink:
nam685/chatbot@8c12676ed47ea16c4f3223524ab02ffd08bcfe08 -
Branch / Tag:
refs/tags/v1.0.0 - Owner: https://github.com/nam685
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
github_cd.yaml@8c12676ed47ea16c4f3223524ab02ffd08bcfe08 -
Trigger Event:
release
-
Statement type: