presenton/servers/fastapi
Saurav Niraula 3ad1e59a46
Merge pull request #260 from presenton/feat/llm-client-error-handling
feat(fastapi): adds better error handling for LLMClient
2025-08-30 16:39:13 +05:45
..
api Merge pull request #260 from presenton/feat/llm-client-error-handling 2025-08-30 16:39:13 +05:45
assets fix(fastapi): replaces fastembed_vectorstore with chroma for ARM compatibility 2025-07-28 12:56:41 +05:45
constants style: remove ollama icons 2025-08-09 03:47:52 +05:45
enums feat(fastapi): adding llm agent that supports tool calls and handling 2025-08-07 04:44:39 +05:45
models feat: implement image upload, retrieval & deletetion endpoints, Also implemented on Nextjs 2025-08-29 20:04:18 +05:45
services feat: implement image upload, retrieval & deletetion endpoints, Also implemented on Nextjs 2025-08-29 20:04:18 +05:45
static style: remove ollama icons 2025-08-09 03:47:52 +05:45
tests Merged with main 2025-08-05 22:37:25 +05:45
utils feat(fastapi): adds better error handling for LLMClient 2025-08-30 14:30:58 +05:45
.python-version feat(fastapi): adds a score based chunker to chunk documents for outlines 2025-08-03 16:33:55 +05:45
mcp_server.py feat: openai spec based mcp server fastmcp 2025-08-18 13:36:29 +05:45
openai_spec.json update: add new endpoint mcp for custom templates list 2025-08-18 14:01:37 +05:45
pyproject.toml feat(fastapi): generate and stream implementation for openai with agentic behavior 2025-08-08 02:49:51 +05:45
server.py Merged with main 2025-08-05 22:37:25 +05:45
uv.lock feat(fastapi): generate and stream implementation for openai with agentic behavior 2025-08-08 02:49:51 +05:45