apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-26 00:46:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Added GCP and Minikube output (#59)

Browse source 
* Added a config to create Minikube k8s, uses hostpath volumes
* Reworked templater to produce docker compose and minikube output
* Fix config templates
This commit is contained in:
cybermaggedon 2024-09-09 17:16:50 +01:00 • committed by GitHub
parent f661791bbf
commit 0ae6feddb0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
62 changed files with 37961 additions and 7077 deletions
Download patch file Download diff file Expand all files Collapse all files

729
deploy/docker-compose/tg-launch-vertexai-cassandra.yaml Normal file
View file

@ -0,0 +1,729 @@
services:
cassandra:
deploy:
resources:
limits:
cpus: '1.0'
memory: 800M
reservations:
cpus: '0.5'
memory: 800M
environment:
JVM_OPTS: -Xms256M -Xmx256M
image: docker.io/cassandra:4.1.6
ports:
- 9042:9042
restart: on-failure:100
volumes:
- cassandra:/var/lib/cassandra
chunker:
command:
- chunker-token
- -p
- pulsar://pulsar:6650
- --chunk-size
- '250'
- --chunk-overlap
- '15'
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
embeddings:
command:
- embeddings-hf
- -p
- pulsar://pulsar:6650
- -m
- all-MiniLM-L6-v2
deploy:
resources:
limits:
cpus: '1.0'
memory: 400M
reservations:
cpus: '0.5'
memory: 400M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
grafana:
deploy:
resources:
limits:
cpus: '1.0'
memory: 256M
reservations:
cpus: '0.5'
memory: 256M
environment:
GF_ORG_NAME: trustgraph.ai
image: docker.io/grafana/grafana:11.1.4
ports:
- 3000:3000
restart: on-failure:100
volumes:
- grafana-storage:/var/lib/grafana
- ./grafana/provisioning/:/etc/grafana/provisioning/dashboards/
- ./grafana/provisioning/:/etc/grafana/provisioning/datasources/
- ./grafana/dashboards/:/var/lib/grafana/dashboards/
graph-rag:
command:
- graph-rag
- -p
- pulsar://pulsar:6650
- --prompt-request-queue
- non-persistent://tg/request/prompt-rag
- --prompt-response-queue
- non-persistent://tg/response/prompt-rag-response
- --entity-limit
- '50'
- --triple-limit
- '30'
- --max-subgraph-size
- '3000'
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
init-pulsar:
command:
- sh
- -c
- while true; do pulsar-admin --admin-url http://pulsar:8080 tenants create tg
; pulsar-admin --admin-url http://pulsar:8080 namespaces create tg/flow ; pulsar-admin
--admin-url http://pulsar:8080 namespaces create tg/request ; pulsar-admin --admin-url
http://pulsar:8080 namespaces create tg/response ; pulsar-admin --admin-url
http://pulsar:8080 namespaces set-retention --size -1 --time 3m tg/response;
sleep 20; done
deploy:
resources:
limits:
cpus: '1'
memory: 400M
reservations:
cpus: '0.1'
memory: 400M
image: docker.io/apachepulsar/pulsar:3.3.1
restart: on-failure:100
kg-extract-definitions:
command:
- kg-extract-definitions
- -p
- pulsar://pulsar:6650
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
kg-extract-relationships:
command:
- kg-extract-relationships
- -p
- pulsar://pulsar:6650
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
pdf-decoder:
command:
- pdf-decoder
- -p
- pulsar://pulsar:6650
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
prometheus:
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/prom/prometheus:v2.53.2
ports:
- 9090:9090
restart: on-failure:100
volumes:
- ./prometheus:/etc/prometheus/
- prometheus-data:/prometheus
prompt:
command:
- prompt-template
- -p
- pulsar://pulsar:6650
- --text-completion-request-queue
- non-persistent://tg/request/text-completion
- --text-completion-response-queue
- non-persistent://tg/response/text-completion-response
- --definition-template
- '<instructions>
Study the following text and derive definitions for any discovered entities.
Do not provide definitions for entities whose definitions are incomplete
or unknown.
Output relationships in JSON format as an arary of objects with fields:
- entity: the name of the entity
- definition: English text which defines the entity
</instructions>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not use special characters in the abstract text. The
abstract will be written as plain text. Do not add markdown formatting
or headers or prefixes. Do not include null or unknown definitions.
</requirements>'
- --relationship-template
- '<instructions>
Study the following text and derive entity relationships. For each
relationship, derive the subject, predicate and object of the relationship.
Output relationships in JSON format as an arary of objects with fields:
- subject: the subject of the relationship
- predicate: the predicate
- object: the object of the relationship
- object-entity: false if the object is a simple data type: name, value or date. true
if it is an entity.
</instructions>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not use special characters in the abstract text. The
abstract must be written as plain text. Do not add markdown formatting
or headers or prefixes.
</requirements>'
- --knowledge-query-template
- 'Study the following set of knowledge statements. The statements are written
in Cypher format that has been extracted from a knowledge graph. Use only the
provided set of knowledge statements in your response. Do not speculate if the
answer is not found in the provided set of knowledge statements.
Here''s the knowledge statements:
{graph}
Use only the provided knowledge statements to respond to the following:
{query}
'
- --document-query-template
- 'Study the following context. Use only the information provided in the context
in your response. Do not speculate if the answer is not found in the provided
set of knowledge statements.
Here is the context:
{documents}
Use only the provided knowledge statements to respond to the following:
{query}
'
- --rows-template
- '<instructions>
Study the following text and derive objects which match the schema provided.
You must output an array of JSON objects for each object you discover
which matches the schema. For each object, output a JSON object whose fields
carry the name field specified in the schema.
</instructions>
<schema>
{schema}
</schema>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not add markdown formatting or headers or prefixes.
</requirements>'
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
prompt-rag:
command:
- prompt-template
- -p
- pulsar://pulsar:6650
- -i
- non-persistent://tg/request/prompt-rag
- -o
- non-persistent://tg/response/prompt-rag-response
- --text-completion-request-queue
- non-persistent://tg/request/text-completion-rag
- --text-completion-response-queue
- non-persistent://tg/response/text-completion-rag-response
- --definition-template
- '<instructions>
Study the following text and derive definitions for any discovered entities.
Do not provide definitions for entities whose definitions are incomplete
or unknown.
Output relationships in JSON format as an arary of objects with fields:
- entity: the name of the entity
- definition: English text which defines the entity
</instructions>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not use special characters in the abstract text. The
abstract will be written as plain text. Do not add markdown formatting
or headers or prefixes. Do not include null or unknown definitions.
</requirements>'
- --relationship-template
- '<instructions>
Study the following text and derive entity relationships. For each
relationship, derive the subject, predicate and object of the relationship.
Output relationships in JSON format as an arary of objects with fields:
- subject: the subject of the relationship
- predicate: the predicate
- object: the object of the relationship
- object-entity: false if the object is a simple data type: name, value or date. true
if it is an entity.
</instructions>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not use special characters in the abstract text. The
abstract must be written as plain text. Do not add markdown formatting
or headers or prefixes.
</requirements>'
- --knowledge-query-template
- 'Study the following set of knowledge statements. The statements are written
in Cypher format that has been extracted from a knowledge graph. Use only the
provided set of knowledge statements in your response. Do not speculate if the
answer is not found in the provided set of knowledge statements.
Here''s the knowledge statements:
{graph}
Use only the provided knowledge statements to respond to the following:
{query}
'
- --document-query-template
- 'Study the following context. Use only the information provided in the context
in your response. Do not speculate if the answer is not found in the provided
set of knowledge statements.
Here is the context:
{documents}
Use only the provided knowledge statements to respond to the following:
{query}
'
- --rows-template
- '<instructions>
Study the following text and derive objects which match the schema provided.
You must output an array of JSON objects for each object you discover
which matches the schema. For each object, output a JSON object whose fields
carry the name field specified in the schema.
</instructions>
<schema>
{schema}
</schema>
<text>
{text}
</text>
<requirements>
You will respond only with raw JSON format data. Do not provide
explanations. Do not add markdown formatting or headers or prefixes.
</requirements>'
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
pulsar:
command:
- bin/pulsar
- standalone
deploy:
resources:
limits:
cpus: '2.0'
memory: 1500M
reservations:
cpus: '1.0'
memory: 1500M
environment:
PULSAR_MEM: -Xms600M -Xmx600M
image: docker.io/apachepulsar/pulsar:3.3.1
ports:
- 6650:6650
- 8080:8080
restart: on-failure:100
volumes:
- pulsar-data:/pulsar/data
qdrant:
deploy:
resources:
limits:
cpus: '1.0'
memory: 256M
reservations:
cpus: '0.5'
memory: 256M
image: docker.io/qdrant/qdrant:v1.11.1
ports:
- 6333:6333
- 6334:6334
restart: on-failure:100
volumes:
- qdrant:/qdrant/storage
query-doc-embeddings:
command:
- de-query-qdrant
- -p
- pulsar://pulsar:6650
- -t
- http://qdrant:6333
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
query-graph-embeddings:
command:
- ge-query-qdrant
- -p
- pulsar://pulsar:6650
- -t
- http://qdrant:6333
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
query-triples:
command:
- triples-query-cassandra
- -p
- pulsar://pulsar:6650
- -g
- cassandra
deploy:
resources:
limits:
cpus: '0.5'
memory: 512M
reservations:
cpus: '0.1'
memory: 512M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
store-doc-embeddings:
command:
- de-write-qdrant
- -p
- pulsar://pulsar:6650
- -t
- http://qdrant:6333
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
store-graph-embeddings:
command:
- ge-write-qdrant
- -p
- pulsar://pulsar:6650
- -t
- http://qdrant:6333
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
store-triples:
command:
- triples-write-cassandra
- -p
- pulsar://pulsar:6650
- -g
- cassandra
deploy:
resources:
limits:
cpus: '0.5'
memory: 128M
reservations:
cpus: '0.1'
memory: 128M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
text-completion:
command:
- text-completion-vertexai
- -p
- pulsar://pulsar:6650
- -k
- /vertexai/private.json
- -r
- us-central1
- -x
- '4096'
- -t
- '0'
- -m
- gemini-1.0-pro-001
deploy:
resources:
limits:
cpus: '0.5'
memory: 256M
reservations:
cpus: '0.1'
memory: 256M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
volumes:
- ./vertexai:/vertexai
text-completion-rag:
command:
- text-completion-vertexai
- -p
- pulsar://pulsar:6650
- -k
- /vertexai/private.json
- -r
- us-central1
- -x
- '4096'
- -t
- '0'
- -m
- gemini-1.0-pro-001
- -i
- non-persistent://tg/request/text-completion-rag
- -o
- non-persistent://tg/response/text-completion-rag-response
deploy:
resources:
limits:
cpus: '0.5'
memory: 256M
reservations:
cpus: '0.1'
memory: 256M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
volumes:
- ./vertexai:/vertexai
vectorize:
command:
- embeddings-vectorize
- -p
- pulsar://pulsar:6650
deploy:
resources:
limits:
cpus: '1.0'
memory: 512M
reservations:
cpus: '0.5'
memory: 512M
image: docker.io/trustgraph/trustgraph-flow:0.10.0
restart: on-failure:100
volumes:
cassandra: {}
grafana-storage: {}
prometheus-data: {}
pulsar-data: {}
qdrant: {}