Microsoft GraphRAG Installation with Llama.CPP Locally - Step-by-Step Guide

 This video is a step-by-step tutorial to install Microsoft GraphRAG with Llama.cpp and Groq API models with your own data.

Code:

conda create -n graphcpp python=3.11 -y && conda activate graphcpp

./llama-server -m /home/Ubuntu/mymodels/qwen1_5-4b-chat-q4_k_m.gguf -c 8192 -n -1 -t 7 --embeddings

pip install graphrag

mkdir -p ./ragtest/input

cp fahd.txt ragtest/input 

python3 -m graphrag.index --init --root ./ragtest

python3 -m graphrag.index --root ./ragtest

python3 -m graphrag.query --root ./ragtest --method global "Who is Fahd Mirza?"

python3 -m graphrag.query --root ./ragtest --method local "Who is Fahd Mirza and where does he live?"

Settings.yaml

encoding_model: cl100k_base

skip_workflows: []

llm:

  api_key: ${GRAPHRAG_API_KEY}

  type: openai_chat # or azure_openai_chat

  model: mixtral-8x7b-32768

  model_supports_json: false # recommended if this is available for your model.

  api_base: https://api.groq.com/openai/v1

  max_tokens: 8192

  concurrent_requests: 1 # the number of parallel inflight requests that may be made

  tokens_per_minute: 28000 # set a leaky bucket throttle

  requests_per_minute: 29 # set a leaky bucket throttle

  # request_timeout: 180.0

  # api_version: 2024-02-15-preview

  # organization: <organization_id>

  # deployment_name: <azure_model_deployment_name>

  max_retries: 10

  max_retry_wait: 60.0

  sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times

parallelization:

  stagger: 0.3

  # num_threads: 50 # the number of threads to use for parallel processing

async_mode: threaded # or asyncio

embeddings:

  ## parallelization: override the global parallelization settings for embeddings

  async_mode: threaded # or asyncio

  llm:

    api_key: ${GRAPHRAG_API_KEY}

    type: openai_embedding # or azure_openai_embedding

    model: text-embedding-ada-002

    api_base: http://localhost:8080

    batch_size: 1 # the number of documents to send in a single request

    # api_version: 2024-02-15-preview

    # organization: <organization_id>

    # deployment_name: <azure_model_deployment_name>

    # tokens_per_minute: 150_000 # set a leaky bucket throttle

    # requests_per_minute: 10_000 # set a leaky bucket throttle

    # max_retries: 10

    # max_retry_wait: 10.0

    # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times

    # concurrent_requests: 25 # the number of parallel inflight requests that may be made

    # batch_max_tokens: 8191 # the maximum number of tokens to send in a single request

    # target: required # or optional

chunks:

  size: 300

  overlap: 100

  group_by_columns: [id] # by default, we don't allow chunks to cross documents

input:

  type: file # or blob

  file_type: text # or csv

  base_dir: "input"

  file_encoding: utf-8

  file_pattern: ".*\\.txt$"

cache:

  type: file # or blob

  base_dir: "cache"

  # connection_string: <azure_blob_storage_connection_string>

  # container_name: <azure_blob_storage_container_name>

storage:

  type: file # or blob

  base_dir: "output/${timestamp}/artifacts"

  # connection_string: <azure_blob_storage_connection_string>

  # container_name: <azure_blob_storage_container_name>

reporting:

  type: file # or console, blob

  base_dir: "output/${timestamp}/reports"

  # connection_string: <azure_blob_storage_connection_string>

  # container_name: <azure_blob_storage_container_name>

entity_extraction:

  ## llm: override the global llm settings for this task

  ## parallelization: override the global parallelization settings for this task

  ## async_mode: override the global async_mode settings for this task

  prompt: "prompts/entity_extraction.txt"

  entity_types: [organization,person,geo,event]

  max_gleanings: 0

summarize_descriptions:

  ## llm: override the global llm settings for this task

  ## parallelization: override the global parallelization settings for this task

  ## async_mode: override the global async_mode settings for this task

  prompt: "prompts/summarize_descriptions.txt"

  max_length: 500

claim_extraction:

  ## llm: override the global llm settings for this task

  ## parallelization: override the global parallelization settings for this task

  ## async_mode: override the global async_mode settings for this task

  # enabled: true

  prompt: "prompts/claim_extraction.txt"

  description: "Any claims or facts that could be relevant to information discovery."

  max_gleanings: 0

community_report:

  ## llm: override the global llm settings for this task

  ## parallelization: override the global parallelization settings for this task

  ## async_mode: override the global async_mode settings for this task

  prompt: "prompts/community_report.txt"

  max_length: 2000

  max_input_length: 8000

cluster_graph:

  max_cluster_size: 10

embed_graph:

  enabled: false # if true, will generate node2vec embeddings for nodes

  # num_walks: 10

  # walk_length: 40

  # window_size: 2

  # iterations: 3

  # random_seed: 597832

umap:

  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:

  graphml: false

  raw_entities: false

  top_level_nodes: false

local_search:

  # text_unit_prop: 0.5

  # community_prop: 0.1

  # conversation_history_max_turns: 5

  # top_k_mapped_entities: 10

  # top_k_relationships: 10

  # max_tokens: 12000

global_search:

  # max_tokens: 12000

  # data_max_tokens: 12000

  # map_max_tokens: 1000

  # reduce_max_tokens: 2000

  # concurrency: 32