RomanNum3ral
/
cai
mirror of https://github.com/aliasrobotics/cai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
661 Commits 6 Branches 5 Tags 218 MiB
Commit Graph

74 Commits

Author SHA1 Message Date
Mery-Sanz 94def221eb merge with reset-v0.4.0 2025-05-07 10:36:30 +02:00
Mery-Sanz d5797aee75 fix agent command 2025-05-05 10:30:46 +02:00
lidia9 4630b20d88 FIX guardrails.py 2025-05-02 16:29:59 +02:00
lidia9 5de9838f3e LLM_as_judge.py - Some fixes for qwen to work - I commit plenty of prints for the future, they will be all removed 2025-04-30 16:55:11 +02:00
lidia9 ff253e183a LLM AS A JUDGE - works for anthropic 2025-04-30 16:00:50 +02:00
lidia9 7311f48421 small fix - now llm as judge works for openai llms 2025-04-30 15:08:24 +02:00
Mery-Sanz aceb9274f4 test functionalities 2025-04-29 10:30:34 +02:00
Mery-Sanz 702a93b6c3 fix agent and add primary test 2025-04-22 16:32:26 +02:00
Mery-Sanz 49f5ccb235 fix tools 2025-04-22 13:35:42 +02:00
Víctor Mayoral Vilches fa198de051 Fix streaming responses in CAI and examples 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-04-03 10:53:33 +02:00
Víctor Mayoral Vilches 9f5073c3a5 CLI output operational 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-04-03 08:19:42 +02:00
Víctor Mayoral Vilches 47bd38b4aa Fix docs 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-04-02 16:48:23 +02:00
Víctor Mayoral Vilches 62212d04b5 Address issues with litellm and agents SDK 
Squeezed in some additional features such as:
- updated get_version()
- various examples for streaming and non-streaming testing

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-04-02 14:03:00 +02:00
Víctor Mayoral Vilches 988c82823a OLLAMA models working 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-31 21:13:15 +02:00
Víctor Mayoral Vilches d3b6f8a1ed Merge remote-tracking branch 'origin/main' into cai 2025-03-31 13:21:34 +02:00
Víctor Mayoral Vilches 28d98cd3cd Streaming now working for OLLAMA models, but not the rest. Figure it out 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-30 09:21:25 +02:00
Víctor Mayoral Vilches c75c272f36 Made local models work by switching into litellm python APIs 
Still some issues with stream versions which needs further
investigation

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-29 20:17:42 +01:00
Víctor Mayoral Vilches 859799c9f4 CLI responding, but only to proprietary models 
Need to investigate why self-hosted models via OLLAMA fail API-wise

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-28 09:48:16 +01:00
amri369 377ddbace6
Hotfix mcp example (#365) 
Small typo in uv command fixed
 2025-03-27 13:05:30 -04:00
Víctor Mayoral Vilches 34a7bad920 Re-structure under sdk/agents, get CLI mockup 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-27 14:31:38 +01:00
Víctor Mayoral Vilches 5e15abd4d7 Minor changes for alignment 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-26 18:55:21 +01:00
Rohan Mehta bd47a41d0b
MCP example for SSE (#354) 
Simple example with a local SSE server.
 2025-03-26 12:56:35 -04:00
Víctor Mayoral Vilches c64f35eda6 Update docs to integrate CAI, minor refinements 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-26 12:41:45 +01:00
Rohan Mehta 2261aabeeb
Adding Git MCP server example (#343) 
- Adding new example showing a single agent interacting with local MCP
server for git
 2025-03-25 19:54:59 -04:00
Rohan Mehta b5ba22904a
[5/n] MCP tracing (#342) 
## Summary:

Adds tracing and tests for tracing.
- Tools are added to the agents
- Theres a span for the mcp tools lookup
- Functions have MCP data

## Test Plan:

Unit tests
.
 2025-03-25 19:54:28 -04:00
Dmitry Pimenov 5385f8b10e added readme, fixed typo 2025-03-25 16:52:52 -07:00
Dmitry Pimenov 88c8acbc5a fixing lint issues 2025-03-25 16:34:00 -07:00
Dmitry Pimenov 0944390c3f adding Git MCP server example 2025-03-25 16:30:50 -07:00
Rohan Mehta 010022777b [5/n] MCP tracing 
## Summary:

Adds tracing and tests for tracing.
- Tools are added to the agents
- Theres a span for the mcp tools lookup
- Functions have MCP data

## Test Plan:

Unit tests
.
 2025-03-25 19:28:48 -04:00
Dominik Kundel 2104f5400b fix(examples): make sure audio playback finishes 2025-03-25 12:11:33 -07:00
Rohan Mehta de1e9a754d [3/n] Add an MCP stdio example 
### Summary:
Spins up a stdio server with some local files, then asks the model questions.

### Test Plan:
Run the example, see it work.
 2025-03-25 13:24:18 -04:00
Víctor Mayoral Vilches b12b9fe036 Adapt litellm example 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-24 19:49:51 +01:00
Víctor Mayoral Vilches 722601045b Initial re-structuring towards CAI 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-24 19:47:41 +01:00
Víctor Mayoral Vilches 3344d317ff Fix error in example path 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-24 19:47:13 +01:00
Víctor Mayoral Vilches 0113e901d2 Remove independent and isolated model tests 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-24 18:43:46 +01:00
Víctor Mayoral Vilches bf8c8d96d8 Restore structure and place litellm integraton under model_providers 
Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
 2025-03-24 18:39:17 +01:00
Víctor Mayoral Vilches 6d198e8513 Merge branch 'main' of https://github.com/openai/openai-agents-python 2025-03-24 17:26:49 +01:00
Rohan Mehta 4cb011c4d2
Fix Typos (#258) 
Noticed a bunch of typos when reading code, fixing.
 2025-03-23 20:28:14 -04:00
Aviral Garg fdf340495b Fix circular dependency in voice streamed example with cleaner import pattern 2025-03-21 16:26:19 -07:00
Aviral Garg 9473c788ba Fix type-checking for circular dependency in voice streamed example 2025-03-21 16:18:04 -07:00
Aviral Garg 7432347a94 Fix circular dependency in voice streamed example by renaming agents.py to my_workflow.py 2025-03-21 13:25:46 -07:00
Rohan Mehta 1771c1e856 update tests 2025-03-20 13:08:38 -04:00
Dominik Kundel aec066649c fix tests 2025-03-20 09:52:15 -07:00
Dominik Kundel c7ce154637 feat: add voice pipeline support 
> Co-authored-by: rm@openai.com
 2025-03-20 09:43:13 -07:00
Raduan77 65264b6b8a fix typos in /examples 2025-03-20 11:23:57 +01:00
Shyamal H Anadkat 0dec5712db Adds example for financial agent 2025-03-19 22:33:13 -07:00
Rohan Mehta 10aa5555af Introduce tool_use_behavior on agents 2025-03-18 21:55:12 -04:00
Rohan Mehta 2bff04719b
Fix handoffs example use cases (#156) 
## Changes
- In this handoff example, we need to use `first_agent` with
`random_number_tool`, instead of `second_agent` without that tool, since
the user is asking to generate a random number.
- fixed typo in comments
 2025-03-17 15:59:18 -04:00
Rohan Mehta fad23f1a3d
fix typo in agent_lifecycle_example.py (#161) 2025-03-17 15:59:00 -04:00
Rohan Mehta 83ec26d200
fix reasoning order in examples (#186) 
I think we need to put reasoning-related outputs first to encourage CoT
reasoning.
 2025-03-17 15:57:52 -04:00