mirror of
https://github.com/docling-project/docling-mcp.git
synced 2026-05-17 13:10:50 +00:00
Michele Dolfi
56b1402e50
* add llama stack tool for ingestion Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix insert and convert Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * example notebook Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * clean up example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * tune test question Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * install llama stack only on >=3.12 Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add exception for llama_stack_client Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use generic openai-like api Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add llama-index usage Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use new llamastack GH org Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update llama stack gh org Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Apply suggestions from code review Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
5 lines
142 B
Bash
5 lines
142 B
Bash
DOCLING_MCP_LI_OLLAMA_MODEL=granite3.2:latest
|
|
DOCLING_MCP_LI_EMBEDDING_MODEL=BAAI/bge-base-en-v1.5
|
|
|
|
DOCLING_MCP_LLS_URL=http://localhost:8321
|