A minimal LLM network chat server/client app.
Project description
chatthy
An asynchronous terminal server/multiple-client setup for conducting and managing chats with LLMs.
network architecture
- client/server RPC-type architecture
- message signing
- ensure chunk ordering
chat management
- basic chat persistence and management
- set, switch to saved system prompts (personalities)
- manage prompts like chats (as files)
- chat truncation to token length
- rename chat
- profiles (profile x personalities -> sets of chats)
- export chat to local file
context workspace
- context workspace (load/drop files)
- client inject from file
- client inject from other sources, e.g. youtube (trag)
- templates for standard instruction requests (trag)
- context workspace - bench/suspend files (hidden by filename)
tool / agentic use
- (auto) tools (evolve from llama-farm -> trag)
- user defined tool plugins
- server use vdb context at LLM will (tool)
- iterative workflows (refer to llama-farm)
- tool chains
- file edit/write
- file patch/diff
- allow model to manage workspace
RAG
- summaries and standard client instructions (trag)
- server use vdb context on request
- consider best method of pdf conversion / ingestion, OOB
- full arxiv paper ingestion (fvdb) - consolidate into one latex file OOB
- vdb result reranking with context, and winnowing
client interface
- can switch between Anthropic, OpenAI, tabbyAPI providers and models
- streaming
- syntax highlighting
- decent REPL
- REPL command mode
- cut/copy from output
- vimish keys in output
- client-side prompt editing
- client-side chat/message editing (how? temporarily set the input field history?)
- latex rendering (this is tricky in the context of prompt-toolkit, but see flatlatex).
- generation cancellation
miscellaneous / extensions
- design with multimodal models in mind
- image sending and use
- use proper config dir (group?)
- dump default conf if missing
unallocated / out of scope
audio streaming ? workflows (tree of instruction templates) tasks
arXiv paper -> latex / md pdf paper -> latex / md
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
chatthy-0.2.4.tar.gz
(59.4 kB
view details)
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
chatthy-0.2.4-py3-none-any.whl
(48.5 kB
view details)
File details
Details for the file chatthy-0.2.4.tar.gz.
File metadata
- Download URL: chatthy-0.2.4.tar.gz
- Upload date:
- Size: 59.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2c16c6d52e82bc7223bbb7ccebc696ec39e92b1000715e01bd9899a4a12d2165
|
|
| MD5 |
36d7eeafa1fb959e237f5e66a8a89e61
|
|
| BLAKE2b-256 |
b81875908083b15c7d9e7943c72311e8085bb6fd7f2e5f6ed9d9d7ecbe5f5955
|
File details
Details for the file chatthy-0.2.4-py3-none-any.whl.
File metadata
- Download URL: chatthy-0.2.4-py3-none-any.whl
- Upload date:
- Size: 48.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e8d8cf58362d86f1e321763e000a131d2ac51f52170887e9ef7a65d239fe195b
|
|
| MD5 |
27de7b26386bc31e5b9a8ba83cb286c8
|
|
| BLAKE2b-256 |
d17536e50d4b37c2517090faf181d3096986deee4a444904f56716f81f3f8d57
|