Add logviewer project and fix Docker imports

- Add logviewer/: Dozzle web UI (port 9999) + analyze.py CLI tool
- docker-compose.yml: add json-file logging with rotation and labels for index/search
- Fix Dockerfiles: COPY *.py . so all modules are included in image
- Convert all relative imports to flat absolute imports for Docker flat layout
- Rename index/schemas.py → index/index_schemas.py to avoid module name collision with search/schemas.py in test runner
- Update all tests to add service dir to sys.path and use flat imports

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

doc/curl_api_test.md

@@ -0,0 +1,366 @@
+# Curl API Test
+
+## Sources
+
+- Canonical contracts: `doc/ТЗ_на_хакатон_Индексация_и_поиск_по_сообщениям.pdf`
+- Runnable examples and local launch notes: `README.md`
+- Actual local wiring: `docker-compose.yml`
+
+PDF gives the strict request/response schemas for `POST /index`, `POST /sparse_embedding`, and `POST /search`.
+`README.md` adds ready curl examples for the minimal requests.
+This file normalizes both into checks against the current local compose stack.
+
+## Compose Wiring
+
+- `index`: `http://localhost:8001`
+- `search`: `http://localhost:8002`
+- `qdrant`: `http://localhost:6334`
+- Inside compose, services use `QDRANT_URL=http://qdrant:6333`
+- Collection name from `.env`: `evaluation`
+- Vector names from `.env`: `dense` and `sparse`
+
+Note: current `docker-compose.yml` publishes Qdrant as `6334:6333`, while `README.md` still says `localhost:6333`. For local checks in this repo state, use `localhost:6334`.
+
+## Extracted API Requests
+
+### `GET /health`
+
+Both services must answer `200 OK`.
+
+```bash
+curl -sS http://localhost:8001/health
+curl -sS http://localhost:8002/health
+```
+
+Expected shape:
+
+```json
+{"status":"ok"}
+```
+
+### `POST /index`
+
+Schema from the PDF:
+
+- body root: `data`
+- `data.chat`
+- `data.overlap_messages[]`
+- `data.new_messages[]`
+
+Runnable request:
+
+```bash
+curl -sS -X POST http://localhost:8001/index \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "data": {
+      "chat": {
+        "id": "chat-1",
+        "name": "Go Nova",
+        "sn": "chat-1@chat.agent",
+        "type": "channel",
+        "is_public": true
+      },
+      "overlap_messages": [
+        {
+          "id": "1",
+          "time": 1710000000,
+          "text": "Обсуждаем релиз Go",
+          "sender_id": "u1",
+          "file_snippets": "",
+          "parts": [],
+          "mentions": [],
+          "member_event": null,
+          "is_system": false,
+          "is_hidden": false,
+          "is_forward": false,
+          "is_quote": false
+        }
+      ],
+      "new_messages": [
+        {
+          "id": "2",
+          "time": 1710000060,
+          "text": "Релиз Go перенесли на следующую неделю",
+          "sender_id": "u2",
+          "file_snippets": "",
+          "parts": [],
+          "mentions": [],
+          "member_event": null,
+          "is_system": false,
+          "is_hidden": false,
+          "is_forward": false,
+          "is_quote": false
+        }
+      ]
+    }
+  }'
+```
+
+Observed response:
+
+```json
+{
+  "results": [
+    {
+      "page_content": "u1: Обсуждаем релиз Go\nu2: Релиз Go перенесли на следующую неделю",
+      "dense_content": "[2024-03-09 16:00] sender:u1\nОбсуждаем релиз Go\n[2024-03-09 16:01] sender:u2\nРелиз Go перенесли на следующую неделю",
+      "sparse_content": "u1 Обсуждаем релиз Go u2 Релиз Go перенесли на следующую неделю",
+      "message_ids": ["2"]
+    }
+  ]
+}
+```
+
+Note: overlap messages are used as context, but are not included in returned `message_ids`.
+
+### `POST /sparse_embedding`
+
+Schema from the PDF:
+
+- body root: `texts: string[]`
+
+Runnable request:
+
+```bash
+curl -sS -X POST http://localhost:8001/sparse_embedding \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "texts": [
+      "Релиз Go перенесли на следующую неделю",
+      "VK GPT обсуждали в отдельном чате"
+    ]
+  }'
+```
+
+Observed response:
+
+```json
+{
+  "vectors": [
+    {
+      "indices": [275068001, 108710752, 842257583, 1159207840, 2129888840, 703082301],
+      "values": [1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606]
+    },
+    {
+      "indices": [73209461, 751565418, 59863655, 1856729543, 2036701913, 1943620510],
+      "values": [1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606, 1.6652868125369606]
+    }
+  ]
+}
+```
+
+### `POST /search`
+
+Minimal request from `README.md`:
+
+```bash
+curl -sS -X POST http://localhost:8002/search \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "question": {
+      "text": "Что писали про релиз Go?"
+    }
+  }'
+```
+
+Full schema from the PDF:
+
+```json
+{
+  "question": {
+    "text": "Что писали про релиз Go?",
+    "asker": "u2",
+    "asked_on": "2024-03-09",
+    "variants": ["релиз go перенесли?", "обсуждение релиза go"],
+    "hyde": ["В чате пишут, что релиз Go перенесли на следующую неделю."],
+    "keywords": ["релиз", "Go", "перенесли"],
+    "entities": {
+      "people": ["u2"],
+      "emails": [],
+      "documents": [],
+      "names": ["Go"],
+      "links": []
+    },
+    "date_mentions": ["следующая неделя", "2024-03-09"],
+    "date_range": {
+      "from": "2024-03-09T00:00:00Z",
+      "to": "2024-03-10T00:00:00Z"
+    },
+    "search_text": "релиз Go перенесли на следующую неделю"
+  }
+}
+```
+
+## Checks Run
+
+### 1. Health checks
+
+Commands:
+
+```bash
+curl -sS http://localhost:8001/health
+curl -sS http://localhost:8002/health
+```
+
+Observed:
+
+```json
+{"status":"ok"}
+{"status":"ok"}
+```
+
+### 2. Qdrant collection exists, but starts empty
+
+Command:
+
+```bash
+curl -sS http://localhost:6334/collections/evaluation
+```
+
+Observed before manual insert:
+
+- `points_count: 0`
+- `indexed_vectors_count: 0`
+
+This matches the README note that local compose creates the collection, but the template flow does not automatically upsert `/index` output into Qdrant.
+
+### 3. `/index` works
+
+Observed:
+
+- HTTP request completed successfully
+- service returned one chunk
+- returned fields match the contract: `page_content`, `dense_content`, `sparse_content`, `message_ids`
+
+### 4. `/sparse_embedding` works
+
+Observed:
+
+- HTTP request completed successfully
+- response returned `vectors[]`
+- each vector contains `indices[]` and `values[]`
+
+### 5. `/search` on an empty collection returns an empty result
+
+Command:
+
+```bash
+curl -sS -X POST http://localhost:8002/search \
+  -H 'Content-Type: application/json' \
+  -d '{"question":{"text":"Что писали про релиз Go?"}}'
+```
+
+Observed:
+
+```json
+{"results":[]}
+```
+
+This is expected while `evaluation` has no points.
+
+### 6. Manual Qdrant upsert for end-to-end smoke test
+
+To verify `/search` end-to-end, I inserted one synthetic point into local Qdrant with:
+
+- point id `1001`
+- dummy dense vector of size `1024`
+- sparse vector under field `sparse`
+- payload containing `page_content` and `metadata.message_ids=["2"]`
+
+Command:
+
+```bash
+vec=$(awk 'BEGIN{for(i=0;i<1024;i++) printf "%s%d", (i?",":""), (i==0)}')
+curl -sS -X PUT 'http://localhost:6334/collections/evaluation/points?wait=true' \
+  -H 'Content-Type: application/json' \
+  -d "{\"points\":[{\"id\":1001,\"vector\":{\"dense\":[${vec}],\"sparse\":{\"indices\":[1],\"values\":[1.0]}},\"payload\":{\"page_content\":\"u1: Обсуждаем релиз Go\\nu2: Релиз Go перенесли на следующую неделю\",\"metadata\":{\"message_ids\":[\"2\"],\"participants\":[\"u1\",\"u2\"],\"start\":\"2024-03-09T16:00:00Z\",\"end\":\"2024-03-09T16:01:00Z\",\"chat_id\":\"chat-1\",\"chat_name\":\"Go Nova\",\"chat_type\":\"channel\",\"chat_sn\":\"chat-1@chat.agent\"}}}]}"
+```
+
+Observed:
+
+```json
+{"result":{"operation_id":0,"status":"completed"},"status":"ok","time":0.008234969}
+```
+
+Collection state after insert:
+
+- `points_count: 1`
+- `indexed_vectors_count: 1`
+
+### 7. `/search` works after one point is present
+
+Minimal request:
+
+```bash
+curl -sS -X POST http://localhost:8002/search \
+  -H 'Content-Type: application/json' \
+  -d '{"question":{"text":"Что писали про релиз Go?"}}'
+```
+
+Observed:
+
+```json
+{"results":[{"message_ids":["2"]}]}
+```
+
+Enriched request without `date_range`:
+
+```bash
+curl -sS -X POST http://localhost:8002/search \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "question": {
+      "text": "Что писали про релиз Go?",
+      "asker": "u2",
+      "asked_on": "2024-03-09",
+      "variants": ["релиз go перенесли?", "обсуждение релиза go"],
+      "hyde": ["В чате пишут, что релиз Go перенесли на следующую неделю."],
+      "keywords": ["релиз", "Go", "перенесли"],
+      "entities": {
+        "people": ["u2"],
+        "emails": [],
+        "documents": [],
+        "names": ["Go"],
+        "links": []
+      },
+      "date_mentions": ["следующая неделя", "2024-03-09"],
+      "search_text": "релиз Go перенесли на следующую неделю"
+    }
+  }'
+```
+
+Observed:
+
+```json
+{"results":[{"message_ids":["2"]}]}
+```
+
+### 8. Defect: `date_range` request currently fails
+
+The full PDF-shaped request with ISO timestamps in `question.date_range` does not work in the current implementation.
+
+Observed:
+
+```json
+{
+  "detail": "2 validation errors for Range\ngte\n  Input should be a valid number, unable to parse string as a number [type=float_parsing, input_value='2024-03-09T00:00:00Z', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/float_parsing\nlte\n  Input should be a valid number, unable to parse string as a number [type=float_parsing, input_value='2024-03-10T00:00:00Z', input_type=str]\n    For further information visit https://errors.pydantic.dev/2.12/v/float_parsing"
+}
+```
+
+Interpretation:
+
+- the public request schema accepts ISO date strings
+- current `search` code tries to pass them into a numeric `qdrant_client.models.Range`
+- so `date_range` is a real runtime bug in the current local build
+
+## Bottom Line
+
+- `index /health`: OK
+- `search /health`: OK
+- `POST /index`: OK
+- `POST /sparse_embedding`: OK
+- `POST /search` on empty collection: OK, returns empty list
+- `POST /search` after one test point is inserted: OK
+- `POST /search` with enriched request excluding `date_range`: OK
+- `POST /search` with `date_range` from the PDF schema: FAILS in current implementation

docker-compose.yml

@@ -2,7 +2,7 @@ services:
   qdrant:
     image: qdrant/qdrant:v1.14.1
     ports:
-      - "6333:6333"
+      - "6334:6333"
 
   qdrant-init:
     image: curlimages/curl:8.12.1
@@ -44,6 +44,15 @@ services:
       - qdrant
     ports:
       - "8001:8000"
+    logging:
+      driver: json-file
+      options:
+        max-size: "20m"
+        max-file: "5"
+        tag: "index-service"
+        labels: "service"
+    labels:
+      - "service=index-service"
 
   search:
     build:
@@ -55,3 +64,12 @@ services:
         condition: service_completed_successfully
     ports:
       - "8002:8000"
+    logging:
+      driver: json-file
+      options:
+        max-size: "20m"
+        max-file: "5"
+        tag: "search-service"
+        labels: "service"
+    labels:
+      - "service=search-service"

index/Dockerfile

@@ -5,7 +5,7 @@ WORKDIR /app
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-COPY main.py .
+COPY *.py .
 
 ENV HOST=0.0.0.0
 ENV PORT=8000

index/chunking.py

@@ -1,8 +1,8 @@
 """Message-based chunking with window by count, length, and time gap."""
 
-from .cleaning import CleanedMessage, clean_message
+from cleaning import CleanedMessage, clean_message
-from .rendering import render_dense_content, render_page_content, render_sparse_content
+from rendering import render_dense_content, render_page_content, render_sparse_content
-from .schemas import IndexAPIItem, Message
+from index_schemas import IndexAPIItem, Message
 
 WINDOW_MAX_MESSAGES = 10
 WINDOW_MAX_CHARS = 2048

index/main.py

@@ -7,9 +7,9 @@ from fastapi import FastAPI, Request
 from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 
-from .chunking import build_chunks
+from chunking import build_chunks
-from .schemas import IndexAPIRequest, IndexAPIResponse, SparseEmbeddingRequest
+from index_schemas import IndexAPIRequest, IndexAPIResponse, SparseEmbeddingRequest
-from .sparse import embed_sparse_texts
+from sparse import embed_sparse_texts
 
 HOST = os.getenv("HOST", "0.0.0.0")
 PORT = int(os.getenv("PORT", "8004"))

index/rendering.py

@@ -2,7 +2,7 @@
 
 import datetime
 
-from .cleaning import CleanedMessage
+from cleaning import CleanedMessage
 
 
 def _format_time(ts: int) -> str:

index/sparse.py

@@ -2,7 +2,7 @@ import logging
 import os
 from functools import lru_cache
 
-from .schemas import SparseVector
+from index_schemas import SparseVector
 
 SPARSE_MODEL_NAME = "Qdrant/bm25"
 FASTEMBED_CACHE_PATH = "/models/fastembed"

kredit.md

@@ -0,0 +1,3 @@
+team_id: 35230
+vk login: 56aa86799bb9edc4
+vk password: edd89cea9ed0734d00ba6904cf7475d7

logviewer/analyze.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+"""
+CLI tool to query and analyze Docker logs from index-service and search-service.
+
+Usage:
+    python3 analyze.py                        # tail both services, live
+    python3 analyze.py --service search       # filter by service
+    python3 analyze.py --level ERROR          # filter by log level
+    python3 analyze.py --grep "qdrant"        # grep in log message
+    python3 analyze.py --last 100             # last N lines per service
+    python3 analyze.py --since 10m            # since N minutes/hours ago (e.g. 10m, 2h)
+    python3 analyze.py --stats               # show request count / error rate summary
+"""
+
+import argparse
+import json
+import re
+import subprocess
+import sys
+from datetime import datetime, timezone
+
+SERVICES = {
+    "index": "hackaton-index-1",
+    "search": "hackaton-search-1",
+}
+
+
+def _run(cmd: list[str], **kwargs) -> subprocess.CompletedProcess:
+    return subprocess.run(cmd, capture_output=True, text=True, **kwargs)
+
+
+def _detect_container_name(service: str) -> str:
+    """Find the actual running container name for a service."""
+    candidates = [
+        f"hackaton-{service}-1",
+        f"hackaton_{service}_1",
+        f"{service}-1",
+        f"{service}_1",
+    ]
+    result = _run(["docker", "ps", "--format", "{{.Names}}"])
+    running = result.stdout.splitlines()
+    for name in candidates:
+        if name in running:
+            return name
+    # fallback: try matching by label
+    result2 = _run(
+        ["docker", "ps", "--filter", f"label=service={service}-service", "--format", "{{.Names}}"]
+    )
+    names = result2.stdout.strip().splitlines()
+    if names:
+        return names[0]
+    return candidates[0]
+
+
+def _docker_logs(container: str, since: str | None, last: int) -> list[str]:
+    cmd = ["docker", "logs", "--timestamps"]
+    if since:
+        cmd += ["--since", since]
+    if last:
+        cmd += ["--tail", str(last)]
+    cmd.append(container)
+    result = _run(cmd)
+    lines = (result.stdout + result.stderr).splitlines()
+    return lines
+
+
+def _parse_line(raw: str) -> dict:
+    """Try to extract structured fields from a log line."""
+    # Docker prepends an RFC3339 timestamp
+    ts_match = re.match(r"^(\d{4}-\d{2}-\d{2}T[\d:.+Z-]+)\s+(.*)", raw)
+    ts = ""
+    message = raw
+    if ts_match:
+        ts = ts_match.group(1)
+        message = ts_match.group(2)
+
+    level = "INFO"
+    for lvl in ("CRITICAL", "ERROR", "WARNING", "WARN", "INFO", "DEBUG"):
+        if lvl in message.upper():
+            level = lvl if lvl != "WARN" else "WARNING"
+            break
+
+    return {"ts": ts, "level": level, "message": message, "raw": raw}
+
+
+def _color(level: str) -> str:
+    return {
+        "ERROR": "\033[31m",
+        "CRITICAL": "\033[35m",
+        "WARNING": "\033[33m",
+        "INFO": "\033[0m",
+        "DEBUG": "\033[36m",
+    }.get(level, "\033[0m")
+
+
+RESET = "\033[0m"
+
+
+def cmd_tail(args: argparse.Namespace) -> None:
+    services = [args.service] if args.service else list(SERVICES.keys())
+    for svc in services:
+        container = _detect_container_name(svc)
+        lines = _docker_logs(container, args.since, args.last)
+        print(f"\n{'='*60}")
+        print(f"  {svc.upper()} SERVICE  ({container})")
+        print(f"{'='*60}")
+        count = 0
+        for raw in lines:
+            parsed = _parse_line(raw)
+            if args.level and parsed["level"] != args.level.upper():
+                continue
+            if args.grep and args.grep.lower() not in parsed["message"].lower():
+                continue
+            color = _color(parsed["level"])
+            print(f"{color}{parsed['raw']}{RESET}")
+            count += 1
+        print(f"  → {count} lines shown")
+
+
+def cmd_stats(args: argparse.Namespace) -> None:
+    services = [args.service] if args.service else list(SERVICES.keys())
+    for svc in services:
+        container = _detect_container_name(svc)
+        lines = _docker_logs(container, args.since, args.last)
+
+        counts: dict[str, int] = {"ERROR": 0, "WARNING": 0, "INFO": 0, "DEBUG": 0, "CRITICAL": 0}
+        requests = 0
+        errors_5xx = 0
+
+        for raw in lines:
+            parsed = _parse_line(raw)
+            lvl = parsed["level"]
+            counts[lvl] = counts.get(lvl, 0) + 1
+            msg = parsed["message"]
+            if re.search(r'"(GET|POST|PUT|DELETE|PATCH)\s', msg):
+                requests += 1
+            if re.search(r'" 5\d\d ', msg):
+                errors_5xx += 1
+
+        print(f"\n{'='*50}")
+        print(f"  STATS: {svc.upper()} SERVICE")
+        print(f"{'='*50}")
+        print(f"  Total lines : {sum(counts.values())}")
+        print(f"  HTTP requests: {requests}")
+        print(f"  5xx errors  : {errors_5xx}")
+        print(f"  ERROR lines : {counts['ERROR']}")
+        print(f"  WARNING lines: {counts['WARNING']}")
+        print(f"  INFO lines  : {counts['INFO']}")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Analyze Docker logs for index-service and search-service",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog=__doc__,
+    )
+    parser.add_argument("--service", choices=list(SERVICES.keys()), help="Filter by service")
+    parser.add_argument("--level", help="Filter by log level (ERROR, WARNING, INFO, DEBUG)")
+    parser.add_argument("--grep", help="Substring filter on log message")
+    parser.add_argument("--last", type=int, default=200, help="Last N lines per service (default 200)")
+    parser.add_argument("--since", help="Show logs since duration (e.g. 10m, 2h, 30s)")
+    parser.add_argument("--stats", action="store_true", help="Show stats summary instead of log lines")
+
+    args = parser.parse_args()
+
+    try:
+        if args.stats:
+            cmd_stats(args)
+        else:
+            cmd_tail(args)
+    except KeyboardInterrupt:
+        print("\nInterrupted.")
+    except FileNotFoundError:
+        print("ERROR: docker not found in PATH", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

logviewer/docker-compose.yml

@@ -0,0 +1,12 @@
+services:
+  dozzle:
+    image: amir20/dozzle:latest
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+    ports:
+      - "9999:8080"
+    environment:
+      DOZZLE_FILTER: "label=service"
+      DOZZLE_LEVEL: info
+      DOZZLE_ENABLE_ACTIONS: "false"
+    restart: unless-stopped

search/Dockerfile

@@ -5,7 +5,7 @@ WORKDIR /app
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-COPY main.py .
+COPY *.py .
 
 ENV HOST=0.0.0.0
 ENV PORT=8000

search/aggregation.py

@@ -1,7 +1,7 @@
 from typing import Any
 
-from .config import TOP_K
+from config import TOP_K
-from .retrieval import extract_message_ids
+from retrieval import extract_message_ids
 
 
 def aggregate_message_ids(

search/main.py

@@ -9,8 +9,8 @@ from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 from qdrant_client import AsyncQdrantClient
 
-from .aggregation import aggregate_message_ids
+from aggregation import aggregate_message_ids
-from .config import (
+from config import (
     API_KEY,
     HOST,
     HTTP_MAX_RETRIES,
@@ -20,7 +20,7 @@ from .config import (
     logger,
     validate_required_env,
 )
-from .query_builder import (
+from query_builder import (
     build_extra_dense_queries,
     build_primary_query,
     build_sparse_query,
@@ -28,9 +28,9 @@ from .query_builder import (
     embed_dense_multi,
     embed_sparse,
 )
-from .rerank import rerank_points
+from rerank import rerank_points
-from .retrieval import qdrant_search
+from retrieval import qdrant_search
-from .schemas import SearchAPIItem, SearchAPIRequest, SearchAPIResponse, SparseVector
+from schemas import SearchAPIItem, SearchAPIRequest, SearchAPIResponse, SparseVector
 
 
 async def _embed_dense_with_retry(client: httpx.AsyncClient, text: str) -> list[float]:

search/query_builder.py

@@ -6,14 +6,14 @@ from functools import lru_cache
 import httpx
 from fastembed import SparseTextEmbedding
 
-from .config import (
+from config import (
     EMBEDDINGS_DENSE_MODEL,
     EMBEDDINGS_DENSE_URL,
     SPARSE_MODEL_NAME,
     get_upstream_kwargs,
     logger,
 )
-from .schemas import DenseEmbeddingResponse, Question, SparseVector
+from schemas import DenseEmbeddingResponse, Question, SparseVector
 
 
 @lru_cache(maxsize=1)

search/rerank.py

@@ -2,8 +2,8 @@ from typing import Any
 
 import httpx
 
-from .config import RERANK_LIMIT, RERANKER_MODEL, RERANKER_URL, get_upstream_kwargs, logger
+from config import RERANK_LIMIT, RERANKER_MODEL, RERANKER_URL, get_upstream_kwargs, logger
-from .retrieval import extract_page_content
+from retrieval import extract_page_content
 
 
 async def get_rerank_scores(

search/retrieval.py

@@ -2,7 +2,7 @@ from typing import Any
 
 from qdrant_client import AsyncQdrantClient, models
 
-from .config import (
+from config import (
     DENSE_PREFETCH_K,
     QDRANT_COLLECTION_NAME,
     QDRANT_DENSE_VECTOR_NAME,
@@ -11,7 +11,7 @@ from .config import (
     SPARSE_PREFETCH_K,
     logger,
 )
-from .schemas import Question, SparseVector
+from schemas import Question, SparseVector
 
 
 def _build_filter(question: Question) -> models.Filter | None:

tests/test_aggregation.py

@@ -1,15 +1,17 @@
 """Unit tests for search/aggregation.py"""
 import sys
 import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+_SEARCH_DIR = os.path.join(os.path.dirname(__file__), "..", "search")
+sys.path.insert(0, _SEARCH_DIR)
 
 os.environ.setdefault("EMBEDDINGS_DENSE_URL", "http://localhost/embed")
 os.environ.setdefault("RERANKER_URL", "http://localhost/rerank")
 os.environ.setdefault("QDRANT_URL", "http://localhost:6333")
 os.environ.setdefault("API_KEY", "test-key")
 
-from search.aggregation import aggregate_message_ids
+from aggregation import aggregate_message_ids
-from search.config import TOP_K
+from config import TOP_K
 
 
 def _point(message_ids: list[str]):

tests/test_chunking.py

@@ -1,11 +1,13 @@
 """Unit tests for index/chunking.py"""
 import sys
 import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
 
-from index.chunking import build_chunks, _split_windows, WINDOW_MAX_MESSAGES, TIME_GAP_SECONDS
+_INDEX_DIR = os.path.join(os.path.dirname(__file__), "..", "index")
-from index.cleaning import CleanedMessage
+sys.path.insert(0, _INDEX_DIR)
-from index.schemas import Message
+
+from chunking import build_chunks, _split_windows, WINDOW_MAX_MESSAGES, TIME_GAP_SECONDS
+from cleaning import CleanedMessage
+from index_schemas import Message
 
 
 def _make_message(id: str, time: int, text: str = "hello", **kwargs) -> Message:

tests/test_cleaning.py

@@ -1,17 +1,19 @@
 """Unit tests for index/cleaning.py"""
 import sys
 import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+_INDEX_DIR = os.path.join(os.path.dirname(__file__), "..", "index")
+sys.path.insert(0, _INDEX_DIR)
 
 import pytest
-from index.cleaning import (
+from cleaning import (
     normalize_unicode,
     parse_file_snippets,
     normalize_member_event,
     normalize_part,
     clean_message,
 )
-from index.schemas import Message
+from index_schemas import Message
 
 
 def _make_message(**kwargs) -> Message:

tests/test_query_builder.py

@@ -1,7 +1,9 @@
 """Unit tests for search/query_builder.py (pure logic only, no HTTP)"""
 import sys
 import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+_SEARCH_DIR = os.path.join(os.path.dirname(__file__), "..", "search")
+sys.path.insert(0, _SEARCH_DIR)
 
 # Stub env vars before importing search modules
 os.environ.setdefault("EMBEDDINGS_DENSE_URL", "http://localhost/embed")
@@ -9,8 +11,8 @@ os.environ.setdefault("RERANKER_URL", "http://localhost/rerank")
 os.environ.setdefault("QDRANT_URL", "http://localhost:6333")
 os.environ.setdefault("API_KEY", "test-key")
 
-from search.schemas import Entities, Question
+from schemas import Entities, Question
-from search.query_builder import (
+from query_builder import (
     build_primary_query,
     build_extra_dense_queries,
     build_sparse_query,

tests/test_rendering.py

@@ -1,10 +1,12 @@
 """Unit tests for index/rendering.py"""
 import sys
 import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
 
-from index.cleaning import CleanedMessage
+_INDEX_DIR = os.path.join(os.path.dirname(__file__), "..", "index")
-from index.rendering import render_page_content, render_dense_content, render_sparse_content
+sys.path.insert(0, _INDEX_DIR)
+
+from cleaning import CleanedMessage
+from rendering import render_page_content, render_dense_content, render_sparse_content
 
 
 def _make_cleaned(**kwargs) -> CleanedMessage: