Api overview

In [1]:

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License.

# Copyright (c) 2024 Microsoft Corporation. # Licensed under the MIT License.

API Overview¶

This notebook provides a demonstration of how to interact with graphrag as a library using the API as opposed to the CLI. Note that graphrag's CLI actually connects to the library through this API for all operations.

In [2]:

import graphrag.api as api
from graphrag.index.typing import PipelineRunResult

import graphrag.api as api from graphrag.index.typing import PipelineRunResult

Prerequisite¶

As a prerequisite to all API operations, a GraphRagConfig object is required. It is the primary means to control the behavior of graphrag and can be instantiated from a settings.yaml configuration file.

Please refer to the CLI docs for more detailed information on how to generate the settings.yaml file.

Load settings.yaml configuration¶

In [3]:

import yaml

settings = yaml.safe_load(open("<project_directory>/settings.yaml"))  # noqa: PTH123, SIM115

import yaml settings = yaml.safe_load(open("/settings.yaml")) # noqa: PTH123, SIM115

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
Cell In[3], line 3
      1 import yaml
----> 3 settings = yaml.safe_load(open("<project_directory>/settings.yaml"))  # noqa: PTH123, SIM115

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/IPython/core/interactiveshell.py:324, in _modified_open(file, *args, **kwargs)
    317 if file in {0, 1, 2}:
    318     raise ValueError(
    319         f"IPython won't let you open fd={file} by default "
    320         "as it is likely to crash IPython. If you know what you are doing, "
    321         "you can use builtins' open."
    322     )
--> 324 return io_open(file, *args, **kwargs)

FileNotFoundError: [Errno 2] No such file or directory: '<project_directory>/settings.yaml'

At this point, you can modify the imported settings to align with your application's requirements. For example, if building a UI application, the application might need to change the input and/or storage destinations dynamically in order to enable users to build and query different indexes.

Generate a GraphRagConfig object¶

In [4]:

from graphrag.config.create_graphrag_config import create_graphrag_config

graphrag_config = create_graphrag_config(
    values=settings, root_dir="<project_directory>"
)

from graphrag.config.create_graphrag_config import create_graphrag_config graphrag_config = create_graphrag_config( values=settings, root_dir="" )

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 4
      1 from graphrag.config.create_graphrag_config import create_graphrag_config
      3 graphrag_config = create_graphrag_config(
----> 4     values=settings, root_dir="<project_directory>"
      5 )

NameError: name 'settings' is not defined

Indexing API¶

Indexing is the process of ingesting raw text data and constructing a knowledge graph. GraphRAG currently supports plaintext (.txt) and .csv file formats.

Build an index¶

In [5]:

index_result: list[PipelineRunResult] = await api.build_index(config=graphrag_config)

# index_result is a list of workflows that make up the indexing pipeline that was run
for workflow_result in index_result:
    status = f"error\n{workflow_result.errors}" if workflow_result.errors else "success"
    print(f"Workflow Name: {workflow_result.workflow}\tStatus: {status}")

index_result: list[PipelineRunResult] = await api.build_index(config=graphrag_config) # index_result is a list of workflows that make up the indexing pipeline that was run for workflow_result in index_result: status = f"error\n{workflow_result.errors}" if workflow_result.errors else "success" print(f"Workflow Name: {workflow_result.workflow}\tStatus: {status}")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 1
----> 1 index_result: list[PipelineRunResult] = await api.build_index(config=graphrag_config)
      3 # index_result is a list of workflows that make up the indexing pipeline that was run
      4 for workflow_result in index_result:

NameError: name 'graphrag_config' is not defined

Query an index¶

To query an index, several index files must first be read into memory and passed to the query API.

In [6]:

import pandas as pd

final_nodes = pd.read_parquet("<project_directory>/output/create_final_nodes.parquet")
final_entities = pd.read_parquet(
    "<project_directory>/output/create_final_entities.parquet"
)
final_communities = pd.read_parquet(
    "<project_directory>/output/create_final_communities.parquet"
)
final_community_reports = pd.read_parquet(
    "<project_directory>/output/create_final_community_reports.parquet"
)

response, context = await api.global_search(
    config=graphrag_config,
    nodes=final_nodes,
    entities=final_entities,
    communities=final_communities,
    community_reports=final_community_reports,
    community_level=2,
    dynamic_community_selection=False,
    response_type="Multiple Paragraphs",
    query="Who is Scrooge and what are his main relationships?",
)

import pandas as pd final_nodes = pd.read_parquet("/output/create_final_nodes.parquet") final_entities = pd.read_parquet( "/output/create_final_entities.parquet" ) final_communities = pd.read_parquet( "/output/create_final_communities.parquet" ) final_community_reports = pd.read_parquet( "/output/create_final_community_reports.parquet" ) response, context = await api.global_search( config=graphrag_config, nodes=final_nodes, entities=final_entities, communities=final_communities, community_reports=final_community_reports, community_level=2, dynamic_community_selection=False, response_type="Multiple Paragraphs", query="Who is Scrooge and what are his main relationships?", )

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
Cell In[6], line 3
      1 import pandas as pd
----> 3 final_nodes = pd.read_parquet("<project_directory>/output/create_final_nodes.parquet")
      4 final_entities = pd.read_parquet(
      5     "<project_directory>/output/create_final_entities.parquet"
      6 )
      7 final_communities = pd.read_parquet(
      8     "<project_directory>/output/create_final_communities.parquet"
      9 )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/pandas/io/parquet.py:667, in read_parquet(path, engine, columns, storage_options, use_nullable_dtypes, dtype_backend, filesystem, filters, **kwargs)
    664     use_nullable_dtypes = False
    665 check_dtype_backend(dtype_backend)
--> 667 return impl.read(
    668     path,
    669     columns=columns,
    670     filters=filters,
    671     storage_options=storage_options,
    672     use_nullable_dtypes=use_nullable_dtypes,
    673     dtype_backend=dtype_backend,
    674     filesystem=filesystem,
    675     **kwargs,
    676 )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/pandas/io/parquet.py:267, in PyArrowImpl.read(self, path, columns, filters, use_nullable_dtypes, dtype_backend, storage_options, filesystem, **kwargs)
    264 if manager == "array":
    265     to_pandas_kwargs["split_blocks"] = True  # type: ignore[assignment]
--> 267 path_or_handle, handles, filesystem = _get_path_or_handle(
    268     path,
    269     filesystem,
    270     storage_options=storage_options,
    271     mode="rb",
    272 )
    273 try:
    274     pa_table = self.api.parquet.read_table(
    275         path_or_handle,
    276         columns=columns,
   (...)
    279         **kwargs,
    280     )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/pandas/io/parquet.py:140, in _get_path_or_handle(path, fs, storage_options, mode, is_dir)
    130 handles = None
    131 if (
    132     not fs
    133     and not is_dir
   (...)
    138     # fsspec resources can also point to directories
    139     # this branch is used for example when reading from non-fsspec URLs
--> 140     handles = get_handle(
    141         path_or_handle, mode, is_text=False, storage_options=storage_options
    142     )
    143     fs = None
    144     path_or_handle = handles.handle

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/pandas/io/common.py:882, in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
    873         handle = open(
    874             handle,
    875             ioargs.mode,
   (...)
    878             newline="",
    879         )
    880     else:
    881         # Binary mode
--> 882         handle = open(handle, ioargs.mode)
    883     handles.append(handle)
    885 # Convert BytesIO or file objects passed with an encoding

FileNotFoundError: [Errno 2] No such file or directory: '<project_directory>/output/create_final_nodes.parquet'

The response object is the official reponse from graphrag while the context object holds various metadata regarding the querying process used to obtain the final response.

In [7]:

print(response)

print(response)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[7], line 1
----> 1 print(response)

NameError: name 'response' is not defined

Digging into the context a bit more provides users with extremely granular information such as what sources of data (down to the level of text chunks) were ultimately retrieved and used as part of the context sent to the LLM model).

In [8]:

from pprint import pprint

pprint(context)  # noqa: T203

from pprint import pprint pprint(context) # noqa: T203

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[8], line 3
      1 from pprint import pprint
----> 3 pprint(context)  # noqa: T203

NameError: name 'context' is not defined