mirror/temporal-ai-agent
1
0
Fork 0
mirror of https://github.com/temporal-community/temporal-ai-agent.git synced 2026-03-15 14:08:08 +01:00
Code Issues Packages Projects Releases Wiki Activity
300 Commits 11 Branches 4 Tags
jonymusky-litellm-integration
Commit Graph

31 Commits

Author SHA1 Message Date
Jonathan Muszkat
dcb6271c23 feat: LiteLLM integration 2025-05-26 14:20:28 -07:00
Joshua Smith
2a1624f621 back to claud 3.5 
prompts and adding list-agents automatically in goal registry
fixing some finserv tool args
 2025-04-21 09:55:45 -04:00
Joshua Smith
c18a40b502 - dynamic agent prompt based on multi goal or not 
- made choose_agent_goal be dynamically included
- made tool selection not be required in all toolchains
- changes to get env vars easier in workflow
- Updated docs/guides, todo based on aboe
 2025-04-08 15:01:11 -04:00
Joshua Smith
87b5699dc1 documentation & guidance updates, getting things done, fixing a possible NDE if you change env vars, changes to enable user picking "done", minor test changes, minor goal selection prompt improvements 2025-04-03 15:54:44 -04:00
Joshua Smith
40bd76e80f changes to be specific about travel scenarios, setup guidance about goal_categories, fixed a bug about llm selection in tool_activities.py, better comments 2025-03-28 15:33:56 -04:00
Joshua Smith
a3ec7b045a adding move money scenario - still a bit rough but it works 2025-03-26 13:21:13 -04:00
Laine
8d2099fa8e Remove one extra print() statement 2025-03-14 10:26:58 -04:00
Joshua Smith
f969098dc8 finishing grok support 2025-03-12 09:55:25 -04:00
Joshua Smith
6939e3f942 log less chatgpt stuff and actually change the goal 2025-03-11 10:03:45 -04:00
Steve Androulakis
61147136fd pre-warm ollama local model on initialization 2025-02-28 07:31:44 -06:00
Steve Androulakis
71fe9925a8 activity init function to load llm client only once 2025-02-28 07:08:18 -06:00
Steve Androulakis
6fc43a4593 rollback to claude sonnet 3.5 and slight timeout changes 2025-02-25 08:23:09 -06:00
Steve Androulakis
3df2da50b1 upgrade claude sonnet to 3.7 and prompt eng 2025-02-24 15:44:03 -06:00
Steve Androulakis
b37d158770 renaming workflows and activities 2025-02-15 12:12:39 -08:00
Steve Androulakis
0bc4a0e0aa improved performance with openai but not perfect 2025-02-13 08:53:28 -08:00
Steve Androulakis
0db358df47 minor code improvements to workflow 2025-02-04 09:57:52 -08:00
Steve Androulakis
2a2383bb71 prompt validator to prevent going off beaten track 2025-02-03 13:07:27 -08:00
Steve Androulakis
8fbbfef6f7 deepseek api support, dotenv dev fix, other improvements 2025-01-26 21:18:31 -08:00
Steve Androulakis
71b0372e62 anthropic support 2025-01-24 16:59:15 -08:00
Steve Androulakis
c56f45bb86 google gemini 2.0 exp by default 2025-01-24 15:59:14 -08:00
Steve Androulakis
20fdf935ab google gemini support 2025-01-24 15:53:45 -08:00
Steve Androulakis
7977894f64 fixes to issues 1 2 and 3. Plus tuning 2025-01-24 15:23:57 -08:00
Steve Androulakis
f5cf7286a2 works a lot better with 4o! 2025-01-03 15:05:27 -08:00
Steve Androulakis
20d375b4ea vastly improved prompt history 2025-01-03 11:15:01 -08:00
Steve Androulakis
fe3d9b7e90 added confirmation signal step, Temporal is awesome 2025-01-02 10:35:04 -08:00
Steve Androulakis
d1b8e150ba tuning 2025-01-02 10:29:06 -08:00
Steve Androulakis
7398d8dec6 prompt generator overhaul 2025-01-02 10:21:34 -08:00
Steve Androulakis
245d64fca9 LLM planner, not perfect but ok 2025-01-01 16:57:08 -08:00
Steve Androulakis
33af355363 tools functions 2025-01-01 15:30:39 -08:00
Steve Androulakis
eb92c71dfe dynamic activity to call tool 2025-01-01 13:54:54 -08:00
Steve Androulakis
e7e8e7e658 refactor, date context 2025-01-01 13:16:18 -08:00