Small c0069f0a59 fix(ollama): pass tools to client.chat and parse tool_calls from response ...

OllamaLLM.generate_response() never forwarded the tools parameter to
ollama.Client.chat(), and _parse_response() hard-coded tool_calls to an
empty list. This caused graph memory entity extraction to silently return
zero results when using Ollama as the LLM provider.

- Forward tools to client.chat() when provided
- Parse tool_calls from response (supports both dict and object formats)
- Handle string arguments via json.loads

Fixes #4175

Signed-off-by: sxu75374 <imshuaixu@gmail.com>
Signed-off-by: Small <imshuaixu@gmail.com>

2026-03-01 06:55:20 -08:00

..

test_azure_openai_structured.py

[Update] Default LLM (#3587)

2025-10-15 11:19:52 -07:00

test_azure_openai.py

[Update] Default LLM (#3587)

2025-10-15 11:19:52 -07:00

test_deepseek.py

Refactored base class config for llms (#3241)

2025-08-05 15:42:06 -07:00

test_gemini.py

Fix failing tests (#3162)

2025-07-25 00:58:45 +05:30

test_groq.py

Reverting the tools commit (#2404)

2025-03-20 00:09:00 +05:30

test_langchain.py

Tool call support for LangchainLLM (#3542)

2025-10-06 00:03:44 +05:30

test_litellm.py

[Update] Default LLM (#3587)

2025-10-15 11:19:52 -07:00

test_lm_studio.py

Refactored base class config for llms (#3241)

2025-08-05 15:42:06 -07:00

test_ollama.py

fix(ollama): pass tools to client.chat and parse tool_calls from response

2026-03-01 06:55:20 -08:00

test_openai.py

[Update] Default LLM (#3587)

2025-10-15 11:19:52 -07:00

test_together.py

Reverting the tools commit (#2404)

2025-03-20 00:09:00 +05:30

test_vllm.py

Bug fix of thinking llm in vllm (#3510)

2025-10-03 19:13:08 +05:30