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

- search_tools block in litellm-config.yaml (SearXNG as a first-class
  search_provider, standalone /v1/search endpoint, not a model tool) plus
  extra_hosts on the litellm service so it can resolve search.home.
- New embedding-server (nomic-embed-text-v1.5 on a second llama.cpp
  instance), pgvector-db, and litellm-pgvector services — LiteLLM's native
  knowledgebase feature has no Qdrant backend, so this is the only
  self-hosted path (docs/research/litellm-knowledgebase.md).
- vector_store_registry + local-embedding model entry in
  litellm-config.yaml, wiring it together.
- scripts/ingest-memory.sh to load data/memory.md and
  data/claude-legacy-memory.md into the knowledgebase.
- docs/memory-knowledgebase.md documenting the whole setup; data/
  gitignored (personal memory content, not meant to be committed).
- New .env vars (SEARXNG_LAN_IP, PGVECTOR_DB_PASSWORD,
  LITELLM_PGVECTOR_API_KEY, LITELLM_PGVECTOR_EMBEDDING_KEY,
  EMBEDDING_MODEL_FILE) and generate-secrets.sh support for the
  auto-generatable ones.

Resolves #22 and #23 (wayfinder map #21). Not yet verified on real
hardware — see #24.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.env.example

@@ -19,6 +19,15 @@ OPENWEBUI_LITELLM_KEY=
 # Seconds of inactivity before llama-server is stopped. 900 = 15 min.
 LAZYTAINER_INACTIVE_TIMEOUT=900
 
+# --- Embedding model (knowledgebase, see docs/memory-knowledgebase.md) ---
+EMBEDDING_MODEL_FILE=nomic-embed-text-v1.5.Q8_0.gguf
+
+# --- SearXNG web search (see docs/research/litellm-searxng-search.md) ---
+# Required — the litellm container can't resolve search.home's LAN mDNS
+# name on its own; this becomes an extra_hosts entry. Use a static
+# DHCP-reserved IP so it doesn't drift.
+SEARXNG_LAN_IP=
+
 # --- LiteLLM proxy (see docs/proxy-key-onboarding.md, docs/network-access.md) ---
 LITELLM_PORT=4000
 # Required — generate real random values before first run, e.g. `openssl rand -hex 32`.
@@ -33,3 +42,13 @@ LITELLM_DB_PASSWORD=
 # master key never has to be typed into the browser.
 UI_USERNAME=admin
 UI_PASSWORD=
+
+# --- Knowledgebase (pgvector, see docs/memory-knowledgebase.md) ---
+# Required — random values, e.g. `openssl rand -hex 32`.
+PGVECTOR_DB_PASSWORD=
+# Auth key litellm-pgvector requires on its own API (its SERVER_API_KEY).
+LITELLM_PGVECTOR_API_KEY=
+# A virtual key litellm-pgvector uses to call back into litellm for
+# embeddings — create it in the Admin UI like any other workload key
+# (see docs/proxy-key-onboarding.md), name it "litellm-pgvector".
+LITELLM_PGVECTOR_EMBEDDING_KEY=

.gitignore

@@ -1,2 +1,6 @@
 .claude/
 .env
+# Personal memory content ingested by scripts/ingest-memory.sh — not meant
+# to be committed to this repo.
+data/
+.leankg/

README.md

@@ -36,3 +36,7 @@ An [AI gateway/proxy](https://git.arthurerlich.de/haylan/LLM-Server/issues/9) fr
 - Request priority across workloads: [`docs/proxy-request-priority.md`](docs/proxy-request-priority.md).
 
 Open WebUI and the coding CLIs (see [`docs/coding-cli-setup.md`](docs/coding-cli-setup.md)) route through the proxy now — llama-server has no published host port anymore. **Not yet verified**: none of this has been smoke-tested on real hardware (LiteLLM's priority scheduler in particular is beta — see `docs/proxy-request-priority.md`) — see [issue #17](https://git.arthurerlich.de/haylan/LLM-Server/issues/17).
+
+### Web search, knowledgebase, and memory
+
+The gateway also fronts SearXNG-backed web search and a pgvector-backed knowledgebase (loaded with `data/memory.md` / `data/claude-legacy-memory.md`), wired at the LiteLLM layer so every client gets them, not just Open WebUI — see [`docs/memory-knowledgebase.md`](docs/memory-knowledgebase.md). **Not yet verified on real hardware** — see [issue #24](https://git.arthurerlich.de/haylan/LLM-Server/issues/24).

docker-compose.yml

@@ -35,6 +35,36 @@ services:
       - "lazytainer.group.llamaserver.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}"
       - "lazytainer.group.llamaserver.minPacketThreshold=2"
 
+  embedding-server:
+    image: ghcr.io/ggml-org/llama.cpp:server-rocm
+    container_name: embedding-server
+    devices:
+      - /dev/kfd
+      - /dev/dri
+    group_add:
+      - video
+      - render
+    security_opt:
+      - seccomp=unconfined
+    ipc: host
+    volumes:
+      - models:/models
+    command: >
+      -m /models/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}
+      --host 0.0.0.0
+      --port 8080
+      --embeddings
+      --pooling mean
+      --n-gpu-layers 999
+      --ctx-size 8192
+    # A dedicated embedding model — the chat model isn't embedding-trained
+    # and llama.cpp serves one model per process, so this is a second small
+    # instance, not a mode switch on llama-server. See
+    # docs/research/litellm-knowledgebase.md. Small enough (~150MB Q8) to
+    # run alongside the chat model's ~19.6GB in the R9700's 32GB VRAM.
+    restart: unless-stopped
+    networks: [ai-stack]
+
   # ponytail: one-off downloader, not a standing service — run via
   # `docker compose --profile tools run --rm downloader` (see scripts/download-model.sh).
   # Keeps the model file inside the named `models` volume instead of a host bind-mount.
@@ -52,6 +82,20 @@ services:
         curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
         https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
 
+  # ponytail: same one-off pattern as `downloader`, for the embedding model —
+  # run via `docker compose --profile tools run --rm downloader-embedding`.
+  downloader-embedding:
+    image: curlimages/curl:latest
+    profiles: ["tools"]
+    user: root
+    volumes:
+      - models:/models
+    entrypoint: ["sh", "-c"]
+    command:
+      - >
+        curl -L --fail --create-dirs -o /models/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}
+        https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}
+
   qdrant:
     image: qdrant/qdrant:latest
     container_name: qdrant
@@ -107,6 +151,12 @@ services:
     env_file: .env
     environment:
       - DATABASE_URL=postgresql://litellm:${LITELLM_DB_PASSWORD}@litellm-db:5432/litellm
+    # The litellm container only joins the ai-stack bridge network, which has
+    # no visibility into the LAN's mDNS/local-DNS names — search.home won't
+    # resolve without this. Set SEARXNG_LAN_IP in .env to its stable LAN IP
+    # (static DHCP reservation recommended). See docs/research/litellm-searxng-search.md.
+    extra_hosts:
+      - "search.home:${SEARXNG_LAN_IP}"
     command: ["--config", "/app/config.yaml", "--port", "4000"]
     ports:
       # published for LAN access (proxy.ai.home) and, via NPM, proxy.ai.haylan.ch —
@@ -141,6 +191,59 @@ services:
       timeout: 5s
       retries: 10
 
+  # Separate Postgres instance (with the pgvector extension) for the
+  # knowledgebase — NOT the same database as litellm-db, which is plain
+  # postgres:16-alpine and has no vector extension installed. See
+  # docs/research/litellm-knowledgebase.md.
+  pgvector-db:
+    image: pgvector/pgvector:pg16
+    container_name: pgvector-db
+    env_file: .env
+    environment:
+      - POSTGRES_USER=litellm_pgvector
+      - POSTGRES_PASSWORD=${PGVECTOR_DB_PASSWORD}
+      - POSTGRES_DB=litellm_pgvector
+    volumes:
+      - pgvector-db-data:/var/lib/postgresql/data
+    restart: unless-stopped
+    networks: [ai-stack]
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -d litellm_pgvector -U litellm_pgvector"]
+      interval: 5s
+      timeout: 5s
+      retries: 10
+
+  # LiteLLM's native knowledgebase/vector-store feature has no Qdrant backend
+  # (the qdrant service above only serves Open WebUI's own RAG/Memory) — this
+  # companion service (github.com/BerriAI/litellm-pgvector) is the only
+  # self-hosted path. No published image exists yet, so this builds straight
+  # from the upstream repo. See docs/research/litellm-knowledgebase.md.
+  # ponytail: unverified against real hardware — Prisma migration behavior on
+  # first boot and the exact vector_store_registry field names for the
+  # pg_vector provider need a live smoke test. See issue #24.
+  litellm-pgvector:
+    build:
+      context: https://github.com/BerriAI/litellm-pgvector.git
+    container_name: litellm-pgvector
+    depends_on:
+      pgvector-db:
+        condition: service_healthy
+      litellm:
+        condition: service_healthy
+    environment:
+      - DATABASE_URL=postgresql://litellm_pgvector:${PGVECTOR_DB_PASSWORD}@pgvector-db:5432/litellm_pgvector
+      - SERVER_API_KEY=${LITELLM_PGVECTOR_API_KEY}
+      # Calls back into litellm for embeddings, same pattern as any other
+      # workload — see docs/proxy-key-onboarding.md for issuing this key.
+      - EMBEDDING__MODEL=local-embedding
+      - EMBEDDING__BASE_URL=http://litellm:4000
+      - EMBEDDING__API_KEY=${LITELLM_PGVECTOR_EMBEDDING_KEY}
+      - EMBEDDING__DIMENSIONS=768
+    expose:
+      - "8000"
+    restart: unless-stopped
+    networks: [ai-stack]
+
   lazytainer:
     image: ghcr.io/vmorganp/lazytainer:master
     container_name: lazytainer
@@ -159,3 +262,4 @@ volumes:
   qdrant-data:
   openwebui-data:
   litellm-db-data:
+  pgvector-db-data:

docs/memory-knowledgebase.md

@@ -0,0 +1,64 @@
+# Knowledgebase, memory, and web search
+
+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.
+
+## Web search (SearXNG)
+
+`litellm-config.yaml`'s `search_tools` block wires the LAN's SearXNG instance in as a **standalone REST endpoint**, not a model-callable tool — call it directly:
+
+```bash
+curl http://<proxy>:4000/v1/search/searxng-search \
+  -H "Authorization: Bearer <a virtual key>" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "...", "max_results": 5}'
+```
+
+Because this doesn't ask the model to emit a tool call, it sidesteps Qwen3.8-27B's known-flaky tool-calling (`docs/research/qwen3.8-27b-tool-calling.md`) entirely. Open WebUI's own web-search setting can point at this endpoint the same way.
+
+Requires `SEARXNG_LAN_IP` set in `.env` (SearXNG's stable LAN IP — use a static DHCP reservation) so the `litellm` container can resolve `search.home` via `extra_hosts`. Full research: `docs/research/litellm-searxng-search.md`.
+
+## Knowledgebase (vector store / RAG)
+
+LiteLLM's native knowledgebase feature has **no Qdrant backend** — the `qdrant` service in this stack only serves Open WebUI's own separate RAG/Memory feature and is unrelated to this. The only self-hosted path is [litellm-pgvector](https://github.com/BerriAI/litellm-pgvector), a companion service backed by its own Postgres+pgvector database (`pgvector-db`), which this stack now runs alongside `litellm`. Full research: `docs/research/litellm-knowledgebase.md`.
+
+New pieces:
+
+- **`embedding-server`** — a second llama.cpp instance (small footprint, `nomic-embed-text-v1.5`) serving `/v1/embeddings`. The chat model isn't embedding-trained and llama.cpp serves one model per process, so this can't just be a flag on `llama-server`.
+- **`pgvector-db`** — Postgres with the pgvector extension, separate from `litellm-db`.
+- **`litellm-pgvector`** — the connector service; built straight from its upstream repo (no published image exists).
+- `litellm-config.yaml`'s `local-embedding` model entry and `vector_store_registry` block, tying it together.
+
+### First-time setup
+
+```bash
+docker compose --profile tools run --rm downloader-embedding   # fetch the embedding model
+docker compose up -d embedding-server pgvector-db litellm-pgvector
+```
+
+Create a `litellm-pgvector` virtual key in LiteLLM's Admin UI (per `docs/proxy-key-onboarding.md`) and set it as `LITELLM_PGVECTOR_EMBEDDING_KEY` in `.env` — the connector calls back into `litellm` for embeddings, same as any other workload.
+
+### Loading memory into it
+
+`data/memory.md` and `data/claude-legacy-memory.md` — Claude-memory-style fact files — get loaded via:
+
+```bash
+./scripts/ingest-memory.sh
+```
+
+One chunk per fact/paragraph line, tagged with `source`/`section` metadata. Re-run after editing either file (see the script's header comment for the no-dedup caveat).
+
+### Querying it
+
+Via the OpenAI Assistants-style `file_search` tool on a chat completion:
+
+```json
+{
+  "model": "qwen3.8-27b-local",
+  "messages": [...],
+  "tools": [{"type": "file_search", "vector_store_ids": ["memory-and-notes"]}]
+}
+```
+
+or directly: `POST /v1/vector_stores/memory-and-notes/search` with `{"query": "..."}`.

litellm-config.yaml

@@ -22,6 +22,44 @@ model_list:
       input_cost_per_token: 0.000002   # $2 / MTok
       output_cost_per_token: 0.00001   # $10 / MTok
 
+  - model_name: local-embedding
+    litellm_params:
+      # Served by the dedicated embedding-server (nomic-embed-text-v1.5), not
+      # the chat model — see docker-compose.yml. Called by litellm-pgvector
+      # to embed knowledgebase content, and available directly at
+      # /v1/embeddings for anything else that wants it.
+      model: openai/local-embedding
+      api_base: http://embedding-server:8080/v1
+      api_key: local
+    model_info:
+      mode: embedding
+
+# SearXNG-backed web search — a standalone REST endpoint (/v1/search/searxng-search),
+# NOT a model-callable tool and not auto-injected into chat completions. See
+# docs/research/litellm-searxng-search.md. Requires the litellm container to
+# resolve search.home — see the `extra_hosts` entry in docker-compose.yml.
+search_tools:
+  - search_tool_name: searxng-search
+    litellm_params:
+      search_provider: searxng
+      api_base: http://search.home/
+
+# Knowledgebase / RAG, backed by the litellm-pgvector companion service (NOT
+# Qdrant — LiteLLM's native vector-store feature has no Qdrant provider, see
+# docs/research/litellm-knowledgebase.md). vector_store_id is this proxy's
+# own identifier for the store, not assigned by a backend.
+# ponytail: field names here (custom_llm_provider: pg_vector, api_base
+# pointed at litellm-pgvector) are the best fit from the litellm-pgvector
+# README, not confirmed against a running deploy yet — smoke-test before
+# relying on it. See issue #24.
+vector_store_registry:
+  - vector_store_name: memory-and-notes
+    litellm_params:
+      vector_store_id: "memory-and-notes"
+      custom_llm_provider: pg_vector
+      api_base: http://litellm-pgvector:8000
+      embedding_model: local-embedding
+
 router_settings:
   # ponytail: LiteLLM's request-prioritization scheduler is beta (see
   # docs/proxy-request-priority.md) — exact settings key/shape must be

scripts/generate-secrets.sh

@@ -1,8 +1,8 @@
 #!/usr/bin/env bash
 # Generates random values for the secrets docker-compose.yml requires
-# (LITELLM_MASTER_KEY, LITELLM_SALT_KEY, LITELLM_DB_PASSWORD, UI_PASSWORD)
+# (LITELLM_MASTER_KEY, LITELLM_SALT_KEY, LITELLM_DB_PASSWORD, UI_PASSWORD,
-# and writes them into .env — creating it from .env.example first if it
+# PGVECTOR_DB_PASSWORD, LITELLM_PGVECTOR_API_KEY) and writes them into .env —
-# doesn't exist.
+# creating it from .env.example first if it doesn't exist.
 #
 # ponytail: only fills in blank values, never overwrites ones you've already
 # set — safe to re-run. Re-running won't touch LITELLM_SALT_KEY once it's
@@ -26,5 +26,7 @@ set_if_blank LITELLM_MASTER_KEY "$(openssl rand -hex 32)"
 set_if_blank LITELLM_SALT_KEY "$(openssl rand -hex 32)"
 set_if_blank LITELLM_DB_PASSWORD "$(openssl rand -hex 32)"
 set_if_blank UI_PASSWORD "$(openssl rand -hex 16)"
+set_if_blank PGVECTOR_DB_PASSWORD "$(openssl rand -hex 32)"
+set_if_blank LITELLM_PGVECTOR_API_KEY "$(openssl rand -hex 32)"
 
-echo "Done. Review .env, then set OPENWEBUI_LITELLM_KEY per docs/proxy-key-onboarding.md."
+echo "Done. Review .env, then set OPENWEBUI_LITELLM_KEY, LITELLM_PGVECTOR_EMBEDDING_KEY, and SEARXNG_LAN_IP per docs/proxy-key-onboarding.md and docs/memory-knowledgebase.md."

scripts/ingest-memory.sh

@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+# Loads data/memory.md and data/claude-legacy-memory.md into the LiteLLM
+# knowledgebase (the "memory-and-notes" vector store, see litellm-config.yaml)
+# via litellm-pgvector's batch-embeddings endpoint.
+#
+# ponytail: one chunk per non-empty, non-heading line — both source files are
+# already one fact/paragraph per line (no hard-wrapping), so this needs no
+# real chunking logic. Re-run after editing either file; there's no dedup, so
+# this appends duplicates on a second run against unchanged content — clear
+# the store first (DELETE the vector_store_id's rows) if you need a clean
+# reload.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+[ -f .env ] && set -a && . ./.env && set +a
+
+: "${LITELLM_PGVECTOR_API_KEY:?Set LITELLM_PGVECTOR_API_KEY in .env first}"
+LITELLM_PGVECTOR_URL="${LITELLM_PGVECTOR_URL:-http://localhost:8000}"
+VECTOR_STORE_ID="memory-and-notes"
+
+# Must match litellm-config.yaml's vector_store_registry entry — the
+# registry just points at a store the backend must already know about.
+# Ignores failure if it already exists (no documented idempotency check).
+curl -sf -X POST "${LITELLM_PGVECTOR_URL}/v1/vector_stores" \
+  -H "Authorization: Bearer ${LITELLM_PGVECTOR_API_KEY}" \
+  -H "Content-Type: application/json" \
+  -d "{\"name\": \"${VECTOR_STORE_ID}\"}" > /dev/null 2>&1 || true
+
+ingest_file() {
+  local file="$1" section=""
+  local batch="[]"
+  while IFS= read -r line; do
+    case "$line" in
+      "#"*) section="${line#\# }"; section="${section#\#\# }"; continue ;;
+      ""|"---") continue ;;
+    esac
+    batch=$(jq --arg content "$line" --arg source "$file" --arg section "$section" \
+      '. += [{"content": $content, "metadata": {"source": $source, "section": $section}}]' <<<"$batch")
+  done < "$file"
+
+  echo "Ingesting $(jq 'length' <<<"$batch") chunks from $file..."
+  curl -sf -X POST "${LITELLM_PGVECTOR_URL}/v1/vector_stores/${VECTOR_STORE_ID}/embeddings/batch" \
+    -H "Authorization: Bearer ${LITELLM_PGVECTOR_API_KEY}" \
+    -H "Content-Type: application/json" \
+    -d "$batch" > /dev/null
+}
+
+ingest_file data/memory.md
+ingest_file data/claude-legacy-memory.md
+echo "Done."