Arthur Erlich

haylan closed issue haylan/LLM-Server#23

2026-09-02 19:39:30 +00:00

How does LiteLLM's knowledgebase/vector-store feature work, and what does it need?

haylan pushed to main at haylan/LLM-Server

2026-09-02 19:38:40 +00:00

f508f5670a feat(litellm): wire SearXNG search, pgvector knowledgebase, and memory ingestion

a3ecbc0e02 docs(research): investigate LiteLLM knowledgebase/vector_store feature for #23

8c42f2518b research: LiteLLM web-search + SearXNG wiring (issue #22)

Compare 3 commits »

haylan closed issue haylan/LLM-Server#22

2026-09-02 19:38:40 +00:00

How does LiteLLM's SearXNG web-search integration work, and what does wiring it in require?

haylan opened issue haylan/LLM-Server#24

2026-09-02 19:37:44 +00:00

Verify search + knowledgebase wiring (#21) on the real R9700 box

haylan commented on issue haylan/LLM-Server#23

2026-09-02 19:27:36 +00:00

How does LiteLLM's knowledgebase/vector-store feature work, and what does it need?

Findings (full detail in docs/research/litellm-knowledgebase.md on branch research/litellm-knowledgebase):

Config shape: top-level vector_store_registry list (not under…

haylan pushed to research/litellm-knowledgebase at haylan/LLM-Server

2026-09-02 19:27:25 +00:00

a3ecbc0e02 docs(research): investigate LiteLLM knowledgebase/vector_store feature for #23

8c42f2518b research: LiteLLM web-search + SearXNG wiring (issue #22)

Compare 2 commits »

haylan created branch research/litellm-knowledgebase in haylan/LLM-Server

2026-09-02 19:27:24 +00:00

haylan commented on issue haylan/LLM-Server#22

2026-09-02 19:26:32 +00:00

How does LiteLLM's SearXNG web-search integration work, and what does wiring it in require?

Findings (full doc: https://git.arthurerlich.de/haylan/LLM-Server/src/branch/research/litellm-searxng-search/docs/research/litellm-searxng-search.md)

SearXNG is natively supported.…

haylan created branch research/litellm-searxng-search in haylan/LLM-Server

2026-09-02 19:25:41 +00:00

haylan pushed to research/litellm-searxng-search at haylan/LLM-Server

2026-09-02 19:25:41 +00:00

haylan opened issue haylan/LLM-Server#23

2026-09-02 19:18:55 +00:00

How does LiteLLM's knowledgebase/vector-store feature work, and what does it need?

haylan opened issue haylan/LLM-Server#22

2026-09-02 19:18:54 +00:00

How does LiteLLM's SearXNG web-search integration work, and what does wiring it in require?

haylan opened issue haylan/LLM-Server#21

2026-09-02 19:18:43 +00:00

LiteLLM gateway: search, knowledgebase, and gateway-level memory

haylan deleted branch fix/litellm-reasoning-max-tokens from haylan/LLM-Server

2026-09-02 18:58:19 +00:00

haylan pushed to main at haylan/LLM-Server

2026-09-02 18:58:12 +00:00

949802fb2b Merge pull request 'fix(litellm): default max_tokens=4096 for the reasoning model' (#20) from fix/litellm-reasoning-max-tokens into main

100fed4274 fix(litellm): default max_tokens=4096 for the reasoning model

Compare 2 commits »

haylan merged pull request haylan/LLM-Server#20

2026-09-02 18:58:12 +00:00

fix(litellm): default max_tokens=4096 for the reasoning model

haylan created pull request haylan/LLM-Server#20

2026-09-02 18:55:46 +00:00

fix(litellm): default max_tokens=4096 for the reasoning model

haylan pushed to fix/litellm-reasoning-max-tokens at haylan/LLM-Server

2026-09-02 18:55:41 +00:00

100fed4274 fix(litellm): default max_tokens=4096 for the reasoning model

haylan created branch fix/litellm-reasoning-max-tokens in haylan/LLM-Server

2026-09-02 18:55:41 +00:00

haylan deleted branch fix/litellm-ui-admin-creds from haylan/LLM-Server

2026-09-02 18:29:39 +00:00