diff --git a/.ipynb_checkpoints/README-checkpoint.md b/.ipynb_checkpoints/README-checkpoint.md deleted file mode 100644 index 4aba5b5c..00000000 --- a/.ipynb_checkpoints/README-checkpoint.md +++ /dev/null @@ -1,102 +0,0 @@ - -# TrustGraph - -## Introduction - -TrustGraph is a true end-to-end (e2e) knowledge pipeline that performs a `naive extraction` on a text corpus -to build a RDF style knowledge graph coupled with a `RAG` service compatible with cloud LLMs and open-source -SLMs (Small Language Models). - -The pipeline processing components are interconnected with a pub/sub engine to -maximize modularity and enable new knowledge processing functions. The core processing components decode documents, -chunk text, perform embeddings, apply a local SLM/LLM, call a LLM API, and generate LM predictions. - -The processing showcases the reliability and efficiences of Graph RAG algorithms which can capture -contextual language flags that are missed in conventional RAG approaches. Graph querying algorithms enable retrieving -not just relevant knowledge but language cues essential to understanding semantic uses unique to a text corpus. - -Processing modules are executed in containers. Processing can be scaled-up -by deploying multiple containers. - -### Features - -- PDF decoding -- Text chunking -- Inference of LMs deployed with [Ollama](https://ollama.com) -- Inference of LLMs: Claude, VertexAI and AzureAI serverless endpoints -- Application of a [HuggingFace](https://hf.co) embeddings models -- [RDF](https://www.w3.org/TR/rdf12-schema/)-aligned Knowledge Graph extraction -- Graph edge loading into [Apache Cassandra](https://github.com/apache/cassandra) -- Storing embeddings in [Milvus](https://github.com/milvus-io/milvus) -- Embedding query service -- Graph RAG query service -- All procesing integrates with [Apache Pulsar](https://github.com/apache/pulsar/) -- Containers, so can be deployed using Docker Compose or Kubernetes -- Plug'n'play architecture: switch different LLM modules to suit your needs - -## Architecture - -![architecture](architecture.png) - -TrustGraph is designed to be modular to support as many Language Models and environments as possible. A natural -fit for a modular architecture is to decompose functions into a set modules connected through a pub/sub backbone. -[Apache Pulsar](https://github.com/apache/pulsar/) serves as this pub/sub backbone. Pulsar acts as the data broker -managing inputs and outputs between modules. - -**Pulsar Workflows**: -- For processing flows, Pulsar accepts the output of a processing module - and queues it for input to the next subscribed module. -- For services such as LLMs and embeddings, Pulsar provides a client/server - model. A Pulsar queue is used as the input to the service. When - processed, the output is then delivered to a separate queue where a client - subscriber can request that output. - -The entire architecture, the pub/sub backbone and set of modules, is bundled into a single Python package. A container image with the -package installed can also run the entire architecture. - -## Core Modules - -- `chunker-recursive` - Accepts text documents and uses LangChain recursive - chunking algorithm to produce smaller text chunks. -- `embeddings-hf` - A service which analyses text and returns a vector - embedding using one of the HuggingFace embeddings models. -- `embeddings-vectorize` - Uses an embeddings service to get a vector - embedding which is added to the processor payload. -- `graph-rag` - A query service which applies a Graph RAG algorithm to - provide a response to a text prompt. -- `graph-write-cassandra` - Takes knowledge graph edges and writes them to - a Cassandra store. -- `kg-extract-definitions` - knowledge extractor - examines text and - produces graph edges. - describing discovered terms and also their defintions. Definitions are - derived using the input documents. -- `kg-extract-relationships` - knowledge extractor - examines text and - produces graph edges describing the relationships between discovered - terms. -- `loader` - Takes a document and loads into the processing pipeline. Used - e.g. to add PDF documents. -- `pdf-decoder` - Takes a PDF doc and emits text extracted from the document. - Text extraction from PDF is not a perfect science as PDF is a printable - format. For instance, the wrapping of text between lines in a PDF document - is not semantically encoded, so the decoder will see wrapped lines as - space-separated. -- `vector-write-milvus` - Takes vector-entity mappings and records them - in the vector embeddings store. - -## LM Specific Modules - -- `llm-azure-text` - Sends request to AzureAI serverless endpoint -- `llm-claude-text` - Sends request to Anthropic's API -- `llm-ollama-text` - Sends request to LM running using Ollama -- `llm-vertexai-text` - Sends request to model available through VertexAI API - -## Quickstart Guide - -See [Quickstart on Docker Compose](docs/README.quickstart-docker-compose.md) - -## Development Guide - -See [Development on trustgraph](docs/README.development.md) - - - diff --git a/.ipynb_checkpoints/docker-compose-azure-checkpoint.yaml b/.ipynb_checkpoints/docker-compose-azure-checkpoint.yaml deleted file mode 100644 index ae179cf2..00000000 --- a/.ipynb_checkpoints/docker-compose-azure-checkpoint.yaml +++ /dev/null @@ -1,179 +0,0 @@ - -volumes: - cassandra: - pulsar-conf: - pulsar-data: - etcd: - minio-data: - milvus: - -services: - - cassandra: - image: docker.io/cassandra:4.1.5 - ports: - - "9042:9042" - volumes: - - "cassandra:/var/lib/cassandra" - restart: on-failure:100 - - pulsar: - image: docker.io/apachepulsar/pulsar:3.3.0 - command: bin/pulsar standalone - ports: - - "6650:6650" - - "8080:8080" - volumes: - - "pulsar-conf:/pulsar/conf" - - "pulsar-data:/pulsar/data" - restart: on-failure:100 - - pulsar-manager: - image: docker.io/apachepulsar/pulsar-manager:v0.3.0 - ports: - - "9527:9527" - - "7750:7750" - environment: - SPRING_CONFIGURATION_FILE: /pulsar-manager/pulsar-manager/application.properties - restart: on-failure:100 - - etcd: - image: quay.io/coreos/etcd:v3.5.5 - command: - - "etcd" - - "-advertise-client-urls=http://127.0.0.1:2379" - - "-listen-client-urls" - - "http://0.0.0.0:2379" - - "--data-dir" - - "/etcd" - environment: - ETCD_AUTO_COMPACTION_MODE: revision - ETCD_AUTO_COMPACTION_RETENTION: "1000" - ETCD_QUOTA_BACKEND_BYTES: "4294967296" - ETCD_SNAPSHOT_COUNT: "50000" - ports: - - "2379:2379" - volumes: - - "etcd:/etcd" - restart: on-failure:100 - - minio: - image: docker.io/minio/minio:RELEASE.2024-07-04T14-25-45Z - command: - - "minio" - - "server" - - "/minio_data" - - "--console-address" - - ":9001" - environment: - MINIO_ROOT_USER: minioadmin - MINIO_ROOT_PASSWORD: minioadmin - ports: - - "9001:9001" - volumes: - - "minio-data:/minio_data" - restart: on-failure:100 - - milvus: - image: docker.io/milvusdb/milvus:v2.4.5 - command: - - "milvus" - - "run" - - "standalone" - environment: - ETCD_ENDPOINTS: etcd:2379 - MINIO_ADDRESS: minio:9000 - ports: - - "9091:9091" - - "19530:19530" - volumes: - - "milvus:/var/lib/milvus" - restart: on-failure:100 - - pdf-decoder: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "pdf-decoder" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - chunker: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "chunker-recursive" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - vectorize: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "embeddings-vectorize" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - embeddings: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "embeddings-hf" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - kg-extract-definitions: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "kg-extract-definitions" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - kg-extract-relationships: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "kg-extract-relationships" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 - - vector-write: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "vector-write-milvus" - - "-p" - - "pulsar://pulsar:6650" - - "-t" - - "http://milvus:19530" - restart: on-failure:100 - - graph-write: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "graph-write-cassandra" - - "-p" - - "pulsar://pulsar:6650" - - "-g" - - "cassandra" - restart: on-failure:100 - - llm: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "llm-azure-text" - - "-p" - - "pulsar://pulsar:6650" - - "-k" - - ${AZURE_TOKEN} - - "-e" - - ${AZURE_ENDPOINT} - restart: on-failure:100 - - graph-rag: - image: docker.io/trustgraph/trustgraph-flow:0.1.16 - command: - - "graph-rag" - - "-p" - - "pulsar://pulsar:6650" - restart: on-failure:100 diff --git a/docker-compose-cohere.yaml b/docker-compose-cohere.yaml index e5cf6598..47e8c81c 100644 --- a/docker-compose-cohere.yaml +++ b/docker-compose-cohere.yaml @@ -143,6 +143,10 @@ services: - "chunker-recursive" - "-p" - "pulsar://pulsar:6650" + - "--chunk-size" + - "1000" + - "--chunk-overlap" + - "50" restart: on-failure:100 vectorize: diff --git a/trustgraph/.ipynb_checkpoints/llm_client-checkpoint.py b/trustgraph/.ipynb_checkpoints/llm_client-checkpoint.py deleted file mode 100644 index 4d392f0e..00000000 --- a/trustgraph/.ipynb_checkpoints/llm_client-checkpoint.py +++ /dev/null @@ -1,71 +0,0 @@ -#!/usr/bin/env python3 - -import pulsar -import _pulsar -from pulsar.schema import JsonSchema -from trustgraph.schema import TextCompletionRequest, TextCompletionResponse -import hashlib -import uuid - -# Ugly -ERROR=_pulsar.LoggerLevel.Error -WARN=_pulsar.LoggerLevel.Warn -INFO=_pulsar.LoggerLevel.Info -DEBUG=_pulsar.LoggerLevel.Debug - -class LlmClient: - - def __init__( - self, log_level=ERROR, client_id=None, - pulsar_host="pulsar://pulsar:6650", - ): - - if client_id == None: - client_id = str(uuid.uuid4()) - - self.client = pulsar.Client( - pulsar_host, - logger=pulsar.ConsoleLogger(log_level), - ) - - self.producer = self.client.create_producer( - topic='llm-complete-text', - schema=JsonSchema(TextCompletionRequest), - chunking_enabled=True, - ) - - self.consumer = self.client.subscribe( - 'llm-complete-text-response', client_id, - schema=JsonSchema(TextCompletionResponse), - ) - - def request(self, prompt, timeout=500): - - id = str(uuid.uuid4()) - - r = TextCompletionRequest( - prompt=prompt - ) - - self.producer.send(r, properties={ "id": id }) - - while True: - - msg = self.consumer.receive(timeout_millis=timeout * 1000) - - mid = msg.properties()["id"] - - if mid == id: - resp = msg.value().response - self.consumer.acknowledge(msg) - return resp - - # Ignore messages with wrong ID - self.consumer.acknowledge(msg) - - def __del__(self): - - self.producer.close() - self.consumer.close() - self.client.close() - diff --git a/trustgraph/.ipynb_checkpoints/prompts-checkpoint.py b/trustgraph/.ipynb_checkpoints/prompts-checkpoint.py deleted file mode 100644 index c6b91ff2..00000000 --- a/trustgraph/.ipynb_checkpoints/prompts-checkpoint.py +++ /dev/null @@ -1,138 +0,0 @@ - -def turtle_extract(text): - - prompt = f""" -Study the following text and extract knowledge as -information in Turtle RDF format. -When declaring any new URIs, use prefix, -and declare appropriate namespace tags. - - - -{text} - - - -Do not use placeholders for information you do not know. -You will respond only with raw Turtle RDF 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. -""" - - return prompt - -def scholar(text): - - # Build the prompt for Article style extraction - jsonexample = """{ - "title": "Article title here", - "abstract": "Abstract text here", - "keywords": ["keyword1", "keyword2", "keyword3"], - "people": ["person1", "person2", "person3"] -}""" - - promptscholar = f"""Your task is to read the provided text and write a scholarly abstract to fully explain all of the concepts described in the provided text. The abstract must include all conceptual details. - -{text} - - - -- Structure: For the provided text, write a title, abstract, keywords, - and people for the concepts found in the provided text. Ignore - document formatting in the provided text such as table of contents, - headers, footers, section metadata, and URLs. -- Focus on Concepts The abstract must focus on concepts found in the - provided text. The abstract must be factually accurate. Do not - write any concepts not found in the provided text. Do not - speculate. Do not omit any conceptual details. -- Completeness: The abstract must capture all topics the reader will - need to understand the concepts found in the provided text. Describe - all terms, definitions, entities, people, events, concepts, - conceptual relationships, and any other topics necessary for the - reader to understand the concepts of the provided text. - -- Format: Respond in the form of a valid JSON object. - - -{jsonexample} - - -You will respond only with the JSON object. Do not provide -explanations. Do not use special characters in the abstract text. The -abstract must be written as plain text. -""" - - return promptscholar - -def to_json_ld(text): - - prompt = f""" -Study the following text and output any facts you discover in -well-structured JSON-LD format. -Use any schema you understand from schema.org to describe the facts. - - - -{text} - - - -You will respond only with raw JSON-LD data in JSON format. 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. Do not use information which is not present in -the input text. -""" - - return prompt - - -def to_relationships(text): - - prompt = f""" -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. - - - -{text} - - - -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. -""" - - return prompt - -def to_definitions(text): - - prompt = f""" -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 - - - -{text} - - - -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. -""" - - return prompt - diff --git a/trustgraph/.ipynb_checkpoints/rdf-checkpoint.py b/trustgraph/.ipynb_checkpoints/rdf-checkpoint.py deleted file mode 100644 index b65d9c29..00000000 --- a/trustgraph/.ipynb_checkpoints/rdf-checkpoint.py +++ /dev/null @@ -1,6 +0,0 @@ - -RDF_LABEL = "http://www.w3.org/2000/01/rdf-schema#label" -DEFINITION = "http://www.w3.org/2004/02/skos/core#definition" - -TRUSTGRAPH_ENTITIES = "http://trustgraph.ai/e/" - diff --git a/trustgraph/model/text_completion/cohere/llm.py b/trustgraph/model/text_completion/cohere/llm.py index a0563dc4..22d1281d 100755 --- a/trustgraph/model/text_completion/cohere/llm.py +++ b/trustgraph/model/text_completion/cohere/llm.py @@ -5,6 +5,7 @@ Input is prompt, output is response. """ import cohere +import re from .... schema import TextCompletionRequest, TextCompletionResponse from .... schema import text_completion_request_queue @@ -62,6 +63,7 @@ class Processor(ConsumerProducer): model=self.model, #model='c4ai-aya-23-8b', message=prompt, + preamble = "You are an AI-assistant chatbot. You are trained to read text and find entities in that text. You respond only with well-formed JSON.", temperature=0.0, chat_history=[], prompt_truncation='auto', @@ -72,9 +74,22 @@ class Processor(ConsumerProducer): if event.event_type == "text-generation": resp = event.text print(resp, flush=True) - + + # Parse output for ```json``` delimiters + pattern = r'```json\s*([\s\S]*?)\s*```' + match = re.search(pattern, resp) + + if match: + # If delimiters are found, extract the JSON content + json_content = match.group(1) + json_resp = json_content.strip() + + else: + # If no delimiters are found, return the original text + json_resp = resp.strip() + print("Send response...", flush=True) - r = TextCompletionResponse(response=resp) + r = TextCompletionResponse(response=json_resp) self.send(r, properties={"id": id}) print("Done.", flush=True)