haylan/LLM-Server
1
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: record issue #24's smoke-test findings and local litellm-pgvector patches

Browse Source 
memory-knowledgebase.md no longer says 'not yet verified' — it's been
smoke-tested end-to-end (direct search + the file_search tool on a chat
completion) and the bugs found are fixed in the preceding commits.
VENDORED.md documents the three local patches on top of the upstream
litellm-pgvector commit so a future re-vendor doesn't silently drop them.
This commit is contained in:
haylan
2026-09-02 21:32:38 +00:00
parent 7e8b5069d4
commit 47bdb22457
2 changed files with 23 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/memory-knowledgebase.md
+1 -1
View File
@@ -2,7 +2,7 @@
Three gateway-level capabilities added on top of the [AI gateway/proxy](https://git.arthurerlich.de/haylan/LLM-Server/issues/9), so every client behind LiteLLM gets them — not just Open WebUI. See [issue #21](https://git.arthurerlich.de/haylan/LLM-Server/issues/21) for the rationale.
**Not yet verified on real hardware** — see [issue #24](https://git.arthurerlich.de/haylan/LLM-Server/issues/24). In particular: `litellm-pgvector`'s Prisma migrations on first boot, and the exact `vector_store_registry` field names for the `pg_vector` provider.
**Verified against a live deploy** — see [issue #24](https://git.arthurerlich.de/haylan/LLM-Server/issues/24), closed after smoke-testing found and fixed several bugs: a missing `api_key` in `vector_store_registry` (was silently falling through to the real `api.openai.com`), `litellm-pgvector`'s Prisma schema never actually being pushed to `pgvector-db` (now handled by `./scripts/update.sh`), a 1536- vs 768-dim vector column mismatch, and its create endpoint ignoring any caller-supplied store id (both fixed locally — see `vendor/litellm-pgvector/VENDORED.md`). `scripts/ingest-memory.sh` was also silently broken (posted chunks with no embedding attached) and has been fixed to embed via LiteLLM before inserting.
## Web search (SearXNG)
vendor/litellm-pgvector/VENDORED.md
Vendored
+22 -5
View File
@@ -1,8 +1,25 @@
Vendored from https://github.com/BerriAI/litellm-pgvector at commit
`b553f84a32f580b4303297df5567f25912b59d93` (main, 2026-09-02) — no changes
made to the source. See `docker-compose.yml`'s `litellm-pgvector` service
comment for why this is vendored instead of built from a remote git context.
`b553f84a32f580b4303297df5567f25912b59d93` (main, 2026-09-02). See
`docker-compose.yml`'s `litellm-pgvector` service comment for why this is
vendored instead of built from a remote git context.
**Local changes on top of that commit** (found smoke-testing issue #24 —
without these, the store can never be searched or written to):
- `prisma/schema.prisma`: `Embedding.embedding` was `vector(1536)`
(OpenAI ada-002's size); changed to `vector(768)` to match this stack's
actual embedding model (nomic-embed-text-v1.5).
- `models.py` / `main.py`: `POST /v1/vector_stores` always minted a random
UUID for the new store's `id`, ignoring anything the caller asked for.
Added an optional `id` field to `VectorStoreCreateRequest` and made
`create_vector_store` use it when given — `litellm-config.yaml`'s
`vector_store_registry` addresses this store by a fixed id
(`memory-and-notes`), which never matched a real row otherwise.
Re-applying these after a re-vendor: diff this directory against upstream
before overwriting, or just redo the three edits above.
To update: `git clone https://github.com/BerriAI/litellm-pgvector.git`
somewhere, copy everything except `.git/` over this directory, update the
commit hash above, and run `./scripts/update.sh`.
somewhere, copy everything except `.git/` over this directory, re-apply the
local changes above, update the commit hash above, and run
`./scripts/update.sh`.