tika-docker/docker-compose-tika-vision.yml at main · apache/tika-docker · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Vision-Language Model parsing for tika-server (Tika 4.x).
#
# The pre-4.x inception-rest / Im2txt / inception-video services and the
# org.apache.tika.parser.recognition.ObjectRecognitionParser they served
# have been removed (TIKA-4499 / TIKA-4500). The 4.x replacement is a
# family of VLM parsers (OpenAI-compatible, Anthropic Claude, Google
# Gemini). See:
#
#   docs/modules/ROOT/pages/configuration/parsers/vlm-parsers.adoc
#
# This compose demonstrates the OpenAI-compatible variant pointing at a
# locally-hosted Ollama instance. To use a different VLM:
#   - Swap the mounted tika-config.* for vlm-claude.json or vlm-gemini.json
#     and pass the relevant API key via env (ANTHROPIC_API_KEY /
#     GEMINI_API_KEY).
#   - Drop the vlm-server service block below.

services:

  ## Apache Tika Server
  tika:
    image: apache/tika:latest-full
    command: -c /tika-config.json
    restart: on-failure
    ports:
      - "9998:9998"
    volumes:
      - ./sample-configs/vision/vlm-openai.json:/tika-config.json
      # - ./sample-configs/vision/vlm-claude.json:/tika-config.json
      # - ./sample-configs/vision/vlm-gemini.json:/tika-config.json
    depends_on:
      - vlm-server

  ## Local OpenAI-compatible VLM endpoint.
  ## Replace with vLLM, your own FastAPI wrapper, or remove and point
  ## baseUrl in vlm-openai.json at OpenAI's real API.
  vlm-server:
    image: ollama/ollama:latest
    ports:
      - "8000:11434"
    # Volumes for pulled models. Uncomment and pull a vision-capable model
    # (e.g. `docker exec <container> ollama pull llava`) before first use.
    # volumes:
    #   - ollama-models:/root/.ollama

# volumes:
#   ollama-models: