Die transformasie van CSV-lêers in grafieke met LLM's: 'n Stap-vir-stap-gids

Hoe vaar LLM'e wanneer hulle probeer om grafieke van plat CSV-lêers te skep?

'n Groot deel van my werk is om gebruikers se ervaring met Neo4j te verbeter. Dikwels is dit 'n sleuteluitdaging vir gebruikers, veral in die vroeë dae, om data in Neo4j te kry en dit doeltreffend te modelleer. Alhoewel die aanvanklike datamodel belangrik is en besin moet word, kan dit maklik herfaktoriseer word om prestasie te verbeter namate die datagrootte of aantal gebruikers groei.

Dus, as 'n uitdaging vir myself, het ek gedink ek sal kyk of 'n LLM kan help met die aanvanklike datamodel. As niks anders nie, sal dit demonstreer hoe dinge verbind is en die gebruiker vinnige resultate bied wat hulle aan ander kan wys.

Intuïtief weet ek dat datamodellering 'n iteratiewe proses is, en sekere LLM's kan maklik deur groot hoeveelhede data afgelei word, so dit het 'n goeie geleentheid gebied om LangGraph te gebruik om in siklusse deur die data te werk.

Kom ons duik in die opdragte wat dit laat gebeur het.

Grafiekmodellering Grondbeginsels

Die Graph Data Modeling Fundamentals-kursus op GraphAcademy lei jou deur die basiese beginsels van modellering van data in 'n grafiek, maar as 'n eerste slaag, gebruik ek die volgende reëls:

• Selfstandige naamwoorde word byskrifte - Hulle beskryf die ding wat die nodus verteenwoordig.
• Werkwoorde word verhoudingstipes - Hulle beskryf hoe dinge met mekaar verband hou.
• Alles anders word eienskappe (veral bywoorde) — Jy het 'n naam en mag dalk 'n grys motor bestuur.

Werkwoorde kan ook nodusse wees; jy mag dalk bly wees om te weet dat 'n persoon 'n produk bestel het, maar daardie basiese model laat jou nie toe om te weet waar en wanneer die produk bestel is nie. In hierdie geval word orde 'n nuwe nodus in die model.

Ek is seker dit kan gedistilleer word in 'n aansporing om 'n nul-skoot-benadering vir grafiekdatamodellering te skep.

'n Iteratiewe benadering

Ek het dit 'n paar maande gelede kortliks probeer en gevind dat die model wat ek gebruik, maklik afgelei word wanneer dit met groter skemas te doen het, en die opdragte het redelik vinnig die LLM se tekenlimiete bereik.

Ek het gedink ek sal hierdie keer 'n iteratiewe benadering probeer deur die sleutels een op 'n slag te neem. Dit moet help om afleiding te vermy omdat die LLM net een item op 'n slag hoef te oorweeg.

Die finale benadering het die volgende stappe gebruik:

1. Laai die CSV-lêer in 'n Pandas-dataraam.
2. Ontleed elke kolom in die CSV en voeg dit by 'n datamodel wat losweg op JSON-skema gebaseer is.
3. Identifiseer en voeg ontbrekende unieke ID's vir elke entiteit by.
4. Hersien die datamodel vir akkuraatheid.
5. Genereer Cypher-stellings om die nodusse en verhoudings in te voer.
6. Genereer die unieke beperkings wat die invoerstate onderlê.
7. Skep die beperkings en voer die invoer uit.

Die Data

Ek het vinnig na Kaggle gekyk vir 'n interessante datastel . Die datastel wat uitgestaan het, was Spotify Most Streamed Songs .

 import pandas as pd csv_file = '/Users/adam/projects/datamodeller/data/spotify/spotify-most-streamed-songs.csv' df = pd.read_csv(csv_file) df.head() track_name artist(s)_name artist_count released_year released_month released_day in_spotify_playlists in_spotify_charts streams in_apple_playlists … key mode danceability_% valence_% energy_% acousticness_% instrumentalness_% liveness_% speechiness_% cover_url 0 Seven (feat. Latto) (Explicit Ver.) Latto, Jung Kook 2 2023 7 14 553 147 141381703 43 … B Major 80 89 83 31 0 8 4 Not Found 1 LALA Myke Towers 1 2023 3 23 1474 48 133716286 48 … C# Major 71 61 74 7 0 10 4 https://i.scdn.co/image/ab67616d0000b2730656d5… 2 vampire Olivia Rodrigo 1 2023 6 30 1397 113 140003974 94 … F Major 51 32 53 17 0 31 6 https://i.scdn.co/image/ab67616d0000b273e85259… 3 Cruel Summer Taylor Swift 1 2019 8 23 7858 100 800840817 116 … A Major 55 58 72 11 0 11 15 https://i.scdn.co/image/ab67616d0000b273e787cf… 4 WHERE SHE GOES Bad Bunny 1 2023 5 18 3133 50 303236322 84 … A Minor 65 23 80 14 63 11 6 https://i.scdn.co/image/ab67616d0000b273ab5c9c…

5 rye × 25 kolomme

Dit is relatief eenvoudig, maar ek kan dadelik sien dat daar verhoudings tussen snitte en kunstenaars moet wees.

Daar is ook uitdagings om data-netheid te oorkom, in terme van kolomname en kunstenaars wat komma-geskeide waardes binne die kunstenaar(s)_name-kolom is.

Die keuse van 'n LLM

Ek wou regtig 'n plaaslike LLM hiervoor gebruik, maar ek het vroeg uitgevind dat Llama 3 dit nie sou sny nie. As jy twyfel, val terug op OpenAI:

 from langchain_core.prompts import PromptTemplate from langchain_core.pydantic_v1 import BaseModel, Field from typing import List from langchain_core.output_parsers import JsonOutputParser from langchain_openai import ChatOpenAI llm = ChatOpenAI(model="gpt-4o")

Die skep van 'n datamodel

Ek het 'n verkorte stel modelleringsinstruksies gebruik om die datamodelleringsopdrag te skep. Ek moes 'n paar keer die opdrag ontwerp om 'n konsekwente uitset te kry.

Die nulskoot-voorbeeld het relatief goed gewerk, maar ek het gevind dat die uitset inkonsekwent was. Om 'n gestruktureerde uitset te definieer om die JSON-uitset te hou, het regtig gehelp:

 class JSONSchemaSpecification(BaseModel): notes: str = Field(description="Any notes or comments about the schema") jsonschema: str = Field(description="A JSON array of JSON schema specifications that describe the entities in the data model")

Paar-Shot Voorbeeld Uitset

Die JSON self was ook inkonsekwent, so ek het uiteindelik 'n skema gedefinieer op grond van die filmaanbevelingsdatastel.

Voorbeeld uitset:

 example_output = [ dict( title="Person", type="object", description="Node", properties=[ dict(name="name", column_name="person_name", type="string", description="The name of the person", examples=["Tom Hanks"]), dict(name="date_of_birth", column_name="person_dob", type="date", description="The date of birth for the person", examples=["1987-06-05"]), dict(name="id", column_name="person_name, date_of_birth", type="string", description="The ID is a combination of name and date of birth to ensure uniqueness", examples=["tom-hanks-1987-06-05"]), ], ), dict( title="Director", type="object", description="Node", properties=[ dict(name="name", column_name="director_names", type="string", description="The name of the directors. Split values in column by a comma", examples=["Francis Ford Coppola"]), ], ), dict( title="Movie", type="object", description="Node", properties=[ dict(name="title", column_name="title", type="string", description="The title of the movie", examples=["Toy Story"]), dict(name="released", column_name="released", type="integer", description="The year the movie was released", examples=["1990"]), ], ), dict( title="ACTED_IN", type="object", description="Relationship", properties=[ dict(name="_from", column_name="od", type="string", description="Person found by the `id`. The ID is a combination of name and date of birth to ensure uniqueness", examples=["Person"]), dict(name="_to", column_name="title", type="string", description="The movie title", examples=["Movie"]), dict(name="roles", type="string", column_name="person_roles", description="The roles the person played in the movie", examples=["Woody"]), ], ), dict( title="DIRECTED", type="object", description="Relationship", properties=[ dict(name="_from", type="string", column_name="director_names", description="Director names are comma separated", examples=["Director"]), dict(name="_to", type="string", column_name="title", description="The label of the node this relationship ends at", examples=["Movie"]), ], ), ]

Ek moes van die streng JSON-skema afwyk en die kolomnaam-veld by die uitvoer voeg om die LLM te help om die invoerskrip te genereer. Die verskaffing van voorbeelde van beskrywings het ook in hierdie verband gehelp, anders was die eienskappe wat in die MATCH-klousule gebruik is inkonsekwent.

Die Ketting

Hier is die laaste opdrag:

 model_prompt = PromptTemplate.from_template(""" You are an expert Graph Database administrator. Your task is to design a data model based on the information provided from an existing data source. You must decide where the following column fits in with the existing data model. Consider: * Does the column represent an entity, for example a Person, Place, or Movie? If so, this should be a node in its own right. * Does the column represent a relationship between two entities? If so, this should be a relationship between two nodes. * Does the column represent an attribute of an entity or relationship? If so, this should be a property of a node or relationship. * Does the column represent a shared attribute that could be interesting to query through to find similar nodes, for example a Genre? If so, this should be a node in its own right. ## Instructions for Nodes * Node labels are generally nouns, for example Person, Place, or Movie * Node titles should be in UpperCamelCase ## Instructions for Relationships * Relationshops are generally verbs, for example ACTED_IN, DIRECTED, or PURCHASED * Examples of good relationships are (:Person)-[:ACTED_IN]->(:Movie) or (:Person)-[:PURCHASED]->(:Product) * Relationships should be in UPPER_SNAKE_CASE * Provide any specific instructions for the field in the description. For example, does the field contain a list of comma separated values or a single value? ## Instructions for Properties * Relationships should be in lowerPascalCase * Prefer the shorter name where possible, for example "person_id" and "personId" should simply be "id" * If you are changing the property name from the original field name, mention the column name in the description * Do not include examples for integer or date fields * Always include instructions on data preparation for the field. Does it need to be cast as a string or split into multiple fields on a delimiting value? * Property keys should be letters only, no numbers or special characters. ## Important! Consider the examples provided. Does any data preparation need to be done to ensure the data is in the correct format? You must include any information about data preparation in the description. ## Example Output Here is an example of a good output: {example_output} ## New Data: Key: {key} Data Type: {type} Example Values: {examples} ## Existing Data Model Here is the existing data model: {existing_model} ## Keep Existing Data Model Apply your changes to the existing data model but never remove any existing definitions. """, partial_variables=dict(example_output=dumps(example_output))) model_chain = model_prompt | llm.with_structured_output(JSONSchemaSpecification)

Die uitvoering van die ketting

Om die model iteratief op te dateer, het ek oor die sleutels in die dataraam gegaan en elke sleutel, sy datatipe en die eerste vyf unieke waardes na die prompt deurgegee:

 from json_repair import dumps, loads existing_model = {} for i, key in enumerate(df): print("\n", i, key) print("----------------") try: res = try_chain(model_chain, dict( existing_model=dumps(existing_model), key=key, type=df[key].dtype, examples=dumps(df[key].unique()[:5].tolist()) )) print(res.notes) existing_model = loads(res.jsonschema) print([n['title'] for n in existing_model]) except Exception as e: print(e) pass existing_model

Konsole uitset:

 0 track_name ---------------- Adding 'track_name' to an existing data model. This represents a music track entity. ['Track'] 1 artist(s)_name ---------------- Adding a new column 'artist(s)_name' to the existing data model. This column represents multiple artists associated with tracks and should be modeled as a new node 'Artist' and a relationship 'PERFORMED_BY' from 'Track' to 'Artist'. ['Track', 'Artist', 'PERFORMED_BY'] 2 artist_count ---------------- Added artist_count as a property of Track node. This property indicates the number of artists performing in the track. ['Track', 'Artist', 'PERFORMED_BY'] 3 released_year ---------------- Add the released_year column to the existing data model as a property of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 4 released_month ---------------- Adding the 'released_month' column to the existing data model, considering it as an attribute of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 5 released_day ---------------- Added a new property 'released_day' to the 'Track' node to capture the day of the month a track was released. ['Track', 'Artist', 'PERFORMED_BY'] 6 in_spotify_playlists ---------------- Adding the new column 'in_spotify_playlists' to the existing data model as a property of the 'Track' node. ['Track', 'Artist', 'PERFORMED_BY'] 7 in_spotify_charts ---------------- Adding the 'in_spotify_charts' column to the existing data model as a property of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 8 streams ---------------- Adding a new column 'streams' to the existing data model, representing the number of streams for a track. ['Track', 'Artist', 'PERFORMED_BY'] 9 in_apple_playlists ---------------- Adding new column 'in_apple_playlists' to the existing data model ['Track', 'Artist', 'PERFORMED_BY'] 10 in_apple_charts ---------------- Adding 'in_apple_charts' as a property to the 'Track' node, representing the number of times the track appeared in the Apple charts. ['Track', 'Artist', 'PERFORMED_BY'] 11 in_deezer_playlists ---------------- Add 'in_deezer_playlists' to the existing data model for a music track database. ['Track', 'Artist', 'PERFORMED_BY'] 12 in_deezer_charts ---------------- Adding a new property 'inDeezerCharts' to the existing 'Track' node to represent the number of times the track appeared in Deezer charts. ['Track', 'Artist', 'PERFORMED_BY'] 13 in_shazam_charts ---------------- Adding new data 'in_shazam_charts' to the existing data model. This appears to be an attribute of the 'Track' node, indicating the number of times a track appeared in the Shazam charts. ['Track', 'Artist', 'PERFORMED_BY'] 14 bpm ---------------- Added bpm column as a property to the Track node as it represents a characteristic of the track. ['Track', 'Artist', 'PERFORMED_BY'] 15 key ---------------- Adding the 'key' column to the existing data model. The 'key' represents the musical key of a track, which is a shared attribute that can be interesting to query through to find similar tracks. ['Track', 'Artist', 'PERFORMED_BY'] 16 mode ---------------- Adding 'mode' to the existing data model. It represents a musical characteristic of a track, which is best captured as an attribute of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 17 danceability_% ---------------- Added 'danceability_%' to the existing data model as a property of the Track node. The field represents the danceability percentage of the track. ['Track', 'Artist', 'PERFORMED_BY'] 18 valence_% ---------------- Adding the valence percentage column to the existing data model as a property of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 19 energy_% ---------------- Integration of the new column 'energy_%' into the existing data model. This column represents an attribute of the Track entity and should be added as a property of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 20 acousticness_% ---------------- Adding acousticness_% to the existing data model as a property of the Track node. ['Track', 'Artist', 'PERFORMED_BY'] 21 instrumentalness_% ---------------- Adding the new column 'instrumentalness_%' to the existing Track node as it represents an attribute of the Track entity. ['Track', 'Artist', 'PERFORMED_BY'] 22 liveness_% ---------------- Adding the new column 'liveness_%' to the existing data model as an attribute of the Track node ['Track', 'Artist', 'PERFORMED_BY'] 23 speechiness_% ---------------- Adding the new column 'speechiness_%' to the existing data model as a property of the 'Track' node. ['Track', 'Artist', 'PERFORMED_BY'] 24 cover_url ---------------- Adding a new property 'cover_url' to the existing 'Track' node. This property represents the URL of the track's cover image. ['Track', 'Artist', 'PERFORMED_BY']

Na 'n paar aanpassings aan die opdrag om gebruiksgevalle te hanteer, het ek 'n model gekry waarmee ek baie tevrede was. Die LLM het daarin geslaag om vas te stel dat die datastel bestaan uit Track, Artist, en 'n PERFORMED_BY verhouding om die twee te verbind:

 [ { "title": "Track", "type": "object", "description": "Node", "properties": [ { "name": "name", "column_name": "track_name", "type": "string", "description": "The name of the track", "examples": [ "Seven (feat. Latto) (Explicit Ver.)", "LALA", "vampire", "Cruel Summer", "WHERE SHE GOES", ], }, { "name": "artist_count", "column_name": "artist_count", "type": "integer", "description": "The number of artists performing in the track", "examples": [2, 1, 3, 8, 4], }, { "name": "released_year", "column_name": "released_year", "type": "integer", "description": "The year the track was released", "examples": [2023, 2019, 2022, 2013, 2014], }, { "name": "released_month", "column_name": "released_month", "type": "integer", "description": "The month the track was released", "examples": [7, 3, 6, 8, 5], }, { "name": "released_day", "column_name": "released_day", "type": "integer", "description": "The day of the month the track was released", "examples": [14, 23, 30, 18, 1], }, { "name": "inSpotifyPlaylists", "column_name": "in_spotify_playlists", "type": "integer", "description": "The number of Spotify playlists the track is in. Cast the value as an integer.", "examples": [553, 1474, 1397, 7858, 3133], }, { "name": "inSpotifyCharts", "column_name": "in_spotify_charts", "type": "integer", "description": "The number of times the track appeared in the Spotify charts. Cast the value as an integer.", "examples": [147, 48, 113, 100, 50], }, { "name": "streams", "column_name": "streams", "type": "array", "description": "The list of stream IDs for the track. Maintain the array format.", "examples": [ "141381703", "133716286", "140003974", "800840817", "303236322", ], }, { "name": "inApplePlaylists", "column_name": "in_apple_playlists", "type": "integer", "description": "The number of Apple playlists the track is in. Cast the value as an integer.", "examples": [43, 48, 94, 116, 84], }, { "name": "inAppleCharts", "column_name": "in_apple_charts", "type": "integer", "description": "The number of times the track appeared in the Apple charts. Cast the value as an integer.", "examples": [263, 126, 207, 133, 213], }, { "name": "inDeezerPlaylists", "column_name": "in_deezer_playlists", "type": "array", "description": "The list of Deezer playlist IDs the track is in. Maintain the array format.", "examples": ["45", "58", "91", "125", "87"], }, { "name": "inDeezerCharts", "column_name": "in_deezer_charts", "type": "integer", "description": "The number of times the track appeared in the Deezer charts. Cast the value as an integer.", "examples": [10, 14, 12, 15, 17], }, { "name": "inShazamCharts", "column_name": "in_shazam_charts", "type": "array", "description": "The list of Shazam chart IDs the track is in. Maintain the array format.", "examples": ["826", "382", "949", "548", "425"], }, { "name": "bpm", "column_name": "bpm", "type": "integer", "description": "The beats per minute of the track. Cast the value as an integer.", "examples": [125, 92, 138, 170, 144], }, { "name": "key", "column_name": "key", "type": "string", "description": "The musical key of the track. Cast the value as a string.", "examples": ["B", "C#", "F", "A", "D"], }, { "name": "mode", "column_name": "mode", "type": "string", "description": "The mode of the track (eg, Major, Minor). Cast the value as a string.", "examples": ["Major", "Minor"], }, { "name": "danceability", "column_name": "danceability_%", "type": "integer", "description": "The danceability percentage of the track. Cast the value as an integer.", "examples": [80, 71, 51, 55, 65], }, { "name": "valence", "column_name": "valence_%", "type": "integer", "description": "The valence percentage of the track. Cast the value as an integer.", "examples": [89, 61, 32, 58, 23], }, { "name": "energy", "column_name": "energy_%", "type": "integer", "description": "The energy percentage of the track. Cast the value as an integer.", "examples": [83, 74, 53, 72, 80], }, { "name": "acousticness", "column_name": "acousticness_%", "type": "integer", "description": "The acousticness percentage of the track. Cast the value as an integer.", "examples": [31, 7, 17, 11, 14], }, { "name": "instrumentalness", "column_name": "instrumentalness_%", "type": "integer", "description": "The instrumentalness percentage of the track. Cast the value as an integer.", "examples": [0, 63, 17, 2, 19], }, { "name": "liveness", "column_name": "liveness_%", "type": "integer", "description": "The liveness percentage of the track. Cast the value as an integer.", "examples": [8, 10, 31, 11, 28], }, { "name": "speechiness", "column_name": "speechiness_%", "type": "integer", "description": "The speechiness percentage of the track. Cast the value as an integer.", "examples": [4, 6, 15, 24, 3], }, { "name": "coverUrl", "column_name": "cover_url", "type": "string", "description": "The URL of the track's cover image. If the value is 'Not Found', it should be cast as an empty string.", "examples": [ "https://i.scdn.co/image/ab67616d0000b2730656d5ce813ca3cc4b677e05", "https://i.scdn.co/image/ab67616d0000b273e85259a1cae29a8d91f2093d", ], }, ], }, { "title": "Artist", "type": "object", "description": "Node", "properties": [ { "name": "name", "column_name": "artist(s)_name", "type": "string", "description": "The name of the artist. Split values in column by a comma", "examples": [ "Latto", "Jung Kook", "Myke Towers", "Olivia Rodrigo", "Taylor Swift", "Bad Bunny", ], } ], }, { "title": "PERFORMED_BY", "type": "object", "description": "Relationship", "properties": [ { "name": "_from", "type": "string", "description": "The label of the node this relationship starts at", "examples": ["Track"], }, { "name": "_to", "type": "string", "description": "The label of the node this relationship ends at", "examples": ["Artist"], }, ], }, ] [ { "title": "Track", "type": "object", "description": "Node", "properties": [ { "name": "name", "column_name": "track_name", "type": "string", "description": "The name of the track", "examples": [ "Seven (feat. Latto) (Explicit Ver.)", "LALA", "vampire", "Cruel Summer", "WHERE SHE GOES", ], }, { "name": "artist_count", "column_name": "artist_count", "type": "integer", "description": "The number of artists performing in the track", "examples": [2, 1, 3, 8, 4], }, { "name": "released_year", "column_name": "released_year", "type": "integer", "description": "The year the track was released", "examples": [2023, 2019, 2022, 2013, 2014], }, { "name": "released_month", "column_name": "released_month", "type": "integer", "description": "The month the track was released", "examples": [7, 3, 6, 8, 5], }, { "name": "released_day", "column_name": "released_day", "type": "integer", "description": "The day of the month the track was released", "examples": [14, 23, 30, 18, 1], }, { "name": "inSpotifyPlaylists", "column_name": "in_spotify_playlists", "type": "integer", "description": "The number of Spotify playlists the track is in. Cast the value as an integer.", "examples": [553, 1474, 1397, 7858, 3133], }, { "name": "inSpotifyCharts", "column_name": "in_spotify_charts", "type": "integer", "description": "The number of times the track appeared in the Spotify charts. Cast the value as an integer.", "examples": [147, 48, 113, 100, 50], }, { "name": "streams", "column_name": "streams", "type": "array", "description": "The list of stream IDs for the track. Maintain the array format.", "examples": [ "141381703", "133716286", "140003974", "800840817", "303236322", ], }, { "name": "inApplePlaylists", "column_name": "in_apple_playlists", "type": "integer", "description": "The number of Apple playlists the track is in. Cast the value as an integer.", "examples": [43, 48, 94, 116, 84], }, { "name": "inAppleCharts", "column_name": "in_apple_charts", "type": "integer", "description": "The number of times the track appeared in the Apple charts. Cast the value as an integer.", "examples": [263, 126, 207, 133, 213], }, { "name": "inDeezerPlaylists", "column_name": "in_deezer_playlists", "type": "array", "description": "The list of Deezer playlist IDs the track is in. Maintain the array format.", "examples": ["45", "58", "91", "125", "87"], }, { "name": "inDeezerCharts", "column_name": "in_deezer_charts", "type": "integer", "description": "The number of times the track appeared in the Deezer charts. Cast the value as an integer.", "examples": [10, 14, 12, 15, 17], }, { "name": "inShazamCharts", "column_name": "in_shazam_charts", "type": "array", "description": "The list of Shazam chart IDs the track is in. Maintain the array format.", "examples": ["826", "382", "949", "548", "425"], }, { "name": "bpm", "column_name": "bpm", "type": "integer", "description": "The beats per minute of the track. Cast the value as an integer.", "examples": [125, 92, 138, 170, 144], }, { "name": "key", "column_name": "key", "type": "string", "description": "The musical key of the track. Cast the value as a string.", "examples": ["B", "C#", "F", "A", "D"], }, { "name": "mode", "column_name": "mode", "type": "string", "description": "The mode of the track (eg, Major, Minor). Cast the value as a string.", "examples": ["Major", "Minor"], }, { "name": "danceability", "column_name": "danceability_%", "type": "integer", "description": "The danceability percentage of the track. Cast the value as an integer.", "examples": [80, 71, 51, 55, 65], }, { "name": "valence", "column_name": "valence_%", "type": "integer", "description": "The valence percentage of the track. Cast the value as an integer.", "examples": [89, 61, 32, 58, 23], }, { "name": "energy", "column_name": "energy_%", "type": "integer", "description": "The energy percentage of the track. Cast the value as an integer.", "examples": [83, 74, 53, 72, 80], }, { "name": "acousticness", "column_name": "acousticness_%", "type": "integer", "description": "The acousticness percentage of the track. Cast the value as an integer.", "examples": [31, 7, 17, 11, 14], }, { "name": "instrumentalness", "column_name": "instrumentalness_%", "type": "integer", "description": "The instrumentalness percentage of the track. Cast the value as an integer.", "examples": [0, 63, 17, 2, 19], }, { "name": "liveness", "column_name": "liveness_%", "type": "integer", "description": "The liveness percentage of the track. Cast the value as an integer.", "examples": [8, 10, 31, 11, 28], }, { "name": "speechiness", "column_name": "speechiness_%", "type": "integer", "description": "The speechiness percentage of the track. Cast the value as an integer.", "examples": [4, 6, 15, 24, 3], }, { "name": "coverUrl", "column_name": "cover_url", "type": "string", "description": "The URL of the track's cover image. If the value is 'Not Found', it should be cast as an empty string.", "examples": [ "https://i.scdn.co/image/ab67616d0000b2730656d5ce813ca3cc4b677e05", "https://i.scdn.co/image/ab67616d0000b273e85259a1cae29a8d91f2093d", ], }, ], }, { "title": "Artist", "type": "object", "description": "Node", "properties": [ { "name": "name", "column_name": "artist(s)_name", "type": "string", "description": "The name of the artist. Split values in column by a comma", "examples": [ "Latto", "Jung Kook", "Myke Towers", "Olivia Rodrigo", "Taylor Swift", "Bad Bunny", ], } ], }, { "title": "PERFORMED_BY", "type": "object", "description": "Relationship", "properties": [ { "name": "_from", "type": "string", "description": "The label of the node this relationship starts at", "examples": ["Track"], }, { "name": "_to", "type": "string", "description": "The label of the node this relationship ends at", "examples": ["Artist"], }, ], }, ]

Voeg unieke identifiseerders by

Ek het opgemerk dat die skema geen unieke identifiseerders bevat nie, en dit kan 'n probleem word wanneer dit kom by die invoer van verhoudings. Dit is vanselfsprekend dat verskillende kunstenaars liedjies met dieselfde naam sal vrystel en twee kunstenaars mag dieselfde naam hê.

Om hierdie rede was dit belangrik om 'n identifiseerder vir Tracks te skep sodat hulle binne 'n groter datastel gedifferensieer kon word:

 # Add primary key/unique identifiers uid_prompt = PromptTemplate.from_template(""" You are a graph database expert reviewing a single entity from a data model generated by a colleague. You want to ensure that all of the nodes imported into the database are unique. ## Example A schema contains Actors with a number of properties including name, date of birth. Two actors may have the same name then add a new compound property combining the name and date of birth. If combining values, include the instruction to convert the value to slug case. Call the new property 'id'. If you have identified a new property, add it to the list of properties leaving the rest intact. Include in the description the fields that are to be concatenated. ## Example Output Here is an example of a good output: {example_output} ## Current Entity Schema {entity} """, partial_variables=dict(example_output=dumps(example_output))) uid_chain = uid_prompt | llm.with_structured_output(JSONSchemaSpecification)

Hierdie stap is net regtig nodig vir nodusse, so ek het die nodusse uit die skema onttrek, die ketting vir elkeen uitgevoer en dan die verhoudings gekombineer met die opgedateerde definisies:

 # extract nodes and relationships nodes = [n for n in existing_model if "node" in n["description"].lower()] rels = [n for n in existing_model if "node" not in n["description"].lower()] # generate a unique id for nodes with_uids = [] for entity in nodes: res = uid_chain.invoke(dict(entity=dumps(entity))) json = loads(res.jsonschema) with_uids = with_uids + json if type(json) == list else with_uids + [json] # combine nodes and relationships with_uids = with_uids + rels

Data Model Review

Vir gesonde verstand is dit die moeite werd om die model na te gaan vir optimalisering. Die model_prompt het 'n goeie werk gedoen om die selfstandige naamwoorde en werkwoorde te identifiseer, maar in 'n meer komplekse model.

Een iterasie het die *_playlists en _charts-kolomme as ID's behandel en probeer om Stroomnodusse en IN_PLAYLIST-verhoudings te skep. Ek neem aan dit was as gevolg van die telling van meer as 1 000 insluitend formatering met 'n komma (bv. 1 001).

Goeie idee, maar dalk 'n bietjie te slim. Maar dit wys hoe belangrik dit is om 'n mens in die lus te hê wat die datastruktuur verstaan.

 # Add primary key/unique identifiers review_prompt = PromptTemplate.from_template(""" You are a graph database expert reviewing a data model generated by a colleague. Your task is to review the data model and ensure that it is fit for purpose. Check for: ## Check for nested objects Remember that Neo4j cannot store arrays of objects or nested objects. These must be converted into into separate nodes with relationships between them. You must include the new node and a reference to the relationship to the output schema. ## Check for Entities in properties If there is a property that represents an array of IDs, a new node should be created for that entity. You must include the new node and a reference to the relationship to the output schema. # Keep Instructions Ensure that the instructions for the nodes, relationships, and properties are clear and concise. You may improve them but the detail must not be removed in any circumstances. ## Current Entity Schema {entity} """) review_chain = review_prompt | llm.with_structured_output(JSONSchemaSpecification) review_nodes = [n for n in with_uids if "node" in n["description"].lower() ] review_rels = [n for n in with_uids if "node" not in n["description"].lower() ] reviewed = [] for entity in review_nodes: res = review_chain.invoke(dict(entity=dumps(entity))) json = loads(res.jsonschema) reviewed = reviewed + json # add relationships back in reviewed = reviewed + review_rels len(reviewed) reviewed = with_uids

In 'n werklike scenario wil ek dit 'n paar keer uitvoer om die datamodel iteratief te verbeter. Ek sal 'n maksimum limiet stel, dan herhaal dit tot op daardie punt of die datamodelvoorwerp verander nie meer nie.

Genereer invoerstate

Teen hierdie punt moet die skema robuust genoeg wees en soveel inligting as moontlik insluit om 'n LLM toe te laat om 'n stel invoerskrifte te genereer.

In ooreenstemming met Neo4j-data-invoer aanbevelings , moet die lêer verskeie kere verwerk word, elke keer wat 'n enkele nodus of verhouding ingevoer word om gretige bewerkings en sluiting te vermy.

 import_prompt = PromptTemplate.from_template(""" Based on the data model, write a Cypher statement to import the following data from a CSV file into Neo4j. Do not use LOAD CSV as this data will be imported using the Neo4j Python Driver, use UNWIND on the $rows parameter instead. You are writing a multi-pass import process, so concentrate on the entity mentioned. When importing data, you must use the following guidelines: * follow the instructions in the description when identifying primary keys. * Use the instructions in the description to determine the format of properties when a finding. * When combining fields into an ID, use the apoc.text.slug function to convert any text to slug case and toLower to convert the string to lowercase - apoc.text.slug(toLower(row.`name`)) * If you split a property, convert it to a string and use the trim function to remove any whitespace - trim(toString(row.`name`)) * When combining properties, wrap each property in the coalesce function so the property is not null if one of the values is not set - coalesce(row.`id`, '') + '--'+ coalsece(row.`title`) * Use the `column_name` field to map the CSV column to the property in the data model. * Wrap all column names from the CSV in backticks - for example row.`column_name`. * When you merge nodes, merge on the unique identifier and nothing else. All other properties should be set using `SET`. * Do not use apoc.periodic.iterate, the files will be batched in the application. Data Model: {data_model} Current Entity: {entity} """)

Hierdie ketting vereis 'n ander uitvoervoorwerp as die vorige stappe. In hierdie geval is die sifer-lid die belangrikste, maar ek wou ook 'n chain_of_thought-sleutel insluit om Chain of Thought aan te moedig:

 class CypherOutputSpecification(BaseModel): chain_of_thought: str = Field(description="Any reasoning used to write the Cypher statement") cypher: str = Field(description="The Cypher statement to import the data") notes: Optional[str] = Field(description="Any notes or closing remarks about the Cypher statement") import_chain = import_prompt | llm.with_structured_output(CypherOutputSpecification)

Dieselfde proses is dan van toepassing om oor elk van die hersiene definisies te herhaal en die Cypher te genereer:

 import_cypher = [] for n in reviewed: print('\n\n------', n['title']) res = import_chain.invoke(dict( data_model=dumps(reviewed), entity=n )) import_cypher.append(( res.cypher )) print(res.cypher)

Konsole uitset:

 ------ Track UNWIND $rows AS row MERGE (t:Track {id: apoc.text.slug(toLower(coalesce(row.`track_name`, '') + '-' + coalesce(row.`released_year`, '')))}) SET t.name = trim(toString(row.`track_name`)), t.artist_count = toInteger(row.`artist_count`), t.released_year = toInteger(row.`released_year`), t.released_month = toInteger(row.`released_month`), t.released_day = toInteger(row.`released_day`), t.inSpotifyPlaylists = toInteger(row.`in_spotify_playlists`), t.inSpotifyCharts = toInteger(row.`in_spotify_charts`), t.streams = row.`streams`, t.inApplePlaylists = toInteger(row.`in_apple_playlists`), t.inAppleCharts = toInteger(row.`in_apple_charts`), t.inDeezerPlaylists = row.`in_deezer_playlists`, t.inDeezerCharts = toInteger(row.`in_deezer_charts`), t.inShazamCharts = row.`in_shazam_charts`, t.bpm = toInteger(row.`bpm`), t.key = trim(toString(row.`key`)), t.mode = trim(toString(row.`mode`)), t.danceability = toInteger(row.`danceability_%`), t.valence = toInteger(row.`valence_%`), t.energy = toInteger(row.`energy_%`), t.acousticness = toInteger(row.`acousticness_%`), t.instrumentalness = toInteger(row.`instrumentalness_%`), t.liveness = toInteger(row.`liveness_%`), t.speechiness = toInteger(row.`speechiness_%`), t.coverUrl = CASE row.`cover_url` WHEN 'Not Found' THEN '' ELSE trim(toString(row.`cover_url`)) END ------ Artist UNWIND $rows AS row WITH row, split(row.`artist(s)_name`, ',') AS artistNames UNWIND artistNames AS artistName MERGE (a:Artist {id: apoc.text.slug(toLower(trim(artistName)))}) SET a.name = trim(artistName) ------ PERFORMED_BY UNWIND $rows AS row UNWIND split(row.`artist(s)_name`, ',') AS artist_name MERGE (t:Track {id: apoc.text.slug(toLower(row.`track_name`)) + '-' + trim(toString(row.`released_year`))}) MERGE (a:Artist {id: apoc.text.slug(toLower(trim(artist_name)))}) MERGE (t)-[:PERFORMED_BY]->(a)

Hierdie opdrag het 'n bietjie ingenieurswese geverg om konsekwente resultate te behaal:

• Soms bevat die Cypher MERGE-stelling met veelvuldige velde gedefinieer, wat op sy beste suboptimaal is. As enige van die kolomme nul is, sal die hele invoer misluk.
• Soms sou die resultaat apoc.period.iterate insluit, wat nie meer nodig is nie, en ek wou kode hê wat ek met die Python-bestuurder kon uitvoer.
• Ek moes herhaal dat die gespesifiseerde kolomnaam gebruik moet word wanneer verhoudings geskep word.
• Die LLM sou net nie die instruksies volg wanneer die unieke identifiseerder op die nodusse aan elke kant van die verhouding gebruik word nie, so dit het 'n paar pogings geneem om dit te kry om die instruksies in die beskrywing te volg. Daar was 'n bietjie heen en weer tussen hierdie prompt en die model_prompt.
• Terugmerke was nodig vir die kolomname wat spesiale karakters ingesluit het (bv. energy_%).

Dit sal ook voordelig wees om dit in twee opdragte te verdeel - een vir nodusse en een vir verhoudings. Maar dit is 'n taak vir 'n ander dag.

Skep die unieke beperkings

Vervolgens kan die invoerskrifte as basis gebruik word om unieke beperkings in die databasis te skep:

 constraint_prompt = PromptTemplate.from_template(""" You are an expert graph database administrator. Use the following Cypher statement to write a Cypher statement to create unique constraints on any properties used in a MERGE statement. The correct syntax for a unique constraint is: CREATE CONSTRAINT movie_title_id IF NOT EXISTS FOR (m:Movie) REQUIRE m.title IS UNIQUE; Cypher: {cypher} """) constraint_chain = constraint_prompt | llm.with_structured_output(CypherOutputSpecification) constraint_queries = [] for statement in import_cypher: res = constraint_chain.invoke(dict(cypher=statement)) statements = res.cypher.split(";") for cypher in statements: constraint_queries.append(cypher)

Konsole uitset:

 CREATE CONSTRAINT track_id_unique IF NOT EXISTS FOR (t:Track) REQUIRE t.id IS UNIQUE CREATE CONSTRAINT stream_id IF NOT EXISTS FOR (s:Stream) REQUIRE s.id IS UNIQUE CREATE CONSTRAINT playlist_id IF NOT EXISTS FOR (p:Playlist) REQUIRE p.id IS UNIQUE CREATE CONSTRAINT chart_id IF NOT EXISTS FOR (c:Chart) REQUIRE c.id IS UNIQUE CREATE CONSTRAINT track_id_unique IF NOT EXISTS FOR (t:Track) REQUIRE t.id IS UNIQUE CREATE CONSTRAINT stream_id_unique IF NOT EXISTS FOR (s:Stream) REQUIRE s.id IS UNIQUE CREATE CONSTRAINT track_id_unique IF NOT EXISTS FOR (t:Track) REQUIRE t.id IS UNIQUE CREATE CONSTRAINT playlist_id_unique IF NOT EXISTS FOR (p:Playlist) REQUIRE p.id IS UNIQUE CREATE CONSTRAINT track_id_unique IF NOT EXISTS FOR (track:Track) REQUIRE track.id IS UNIQUE CREATE CONSTRAINT chart_id_unique IF NOT EXISTS FOR (chart:Chart) REQUIRE chart.id IS UNIQUE

Soms sal hierdie aansporing stellings vir indekse en beperkings gee, vandaar die verdeling op die semikolon.

Begin die invoer

Met alles in plek, was dit tyd om die Cypher-stellings uit te voer:

 from os import getenv from neo4j import GraphDatabase driver = GraphDatabase.driver( getenv("NEO4J_URI"), auth=( getenv("NEO4J_USERNAME"), getenv("NEO4J_PASSWORD") ) ) with driver.session() as session: # truncate the db session.run("MATCH (n) DETACH DELETE n") # create constraints for q in constraint_queries: if q.strip() != "": session.run(q) # import the data for q in import_cypher: if q.strip() != "": res = session.run(q, rows=rows).consume() print(q) print(res.counters)

QA op die datastel

Hierdie pos sal nie volledig wees sonder 'n mate van QA op die datastel deur die GraphCypherQACain te gebruik nie:

 from langchain.chains import GraphCypherQAChain from langchain_community.graphs import Neo4jGraph graph = Neo4jGraph( url=getenv("NEO4J_URI"), username=getenv("NEO4J_USERNAME"), password=getenv("NEO4J_PASSWORD"), enhanced_schema=True ) qa = GraphCypherQAChain.from_llm( llm, graph=graph, allow_dangerous_requests=True, verbose=True )

Gewildste kunstenaars

Wie is die gewildste kunstenaars in die databasis?

 qa.invoke({"query": "Who are the most popular artists?"}) > Entering new GraphCypherQAChain chain... Generated Cypher: cypher MATCH (:Track)-[:PERFORMED_BY]->(a:Artist) RETURN a.name, COUNT(*) AS popularity ORDER BY popularity DESC LIMIT 10 Full Context: [{'a.name': 'Bad Bunny', 'popularity': 40}, {'a.name': 'Taylor Swift', 'popularity': 38}, {'a.name': 'The Weeknd', 'popularity': 36}, {'a.name': 'SZA', 'popularity': 23}, {'a.name': 'Kendrick Lamar', 'popularity': 23}, {'a.name': 'Feid', 'popularity': 21}, {'a.name': 'Drake', 'popularity': 19}, {'a.name': 'Harry Styles', 'popularity': 17}, {'a.name': 'Peso Pluma', 'popularity': 16}, {'a.name': '21 Savage', 'popularity': 14}] > Finished chain. { "query": "Who are the most popular artists?", "result": "Bad Bunny, Taylor Swift, and The Weeknd are the most popular artists." }

Dit het gelyk of die LLM gewildheid beoordeel in terme van die aantal snitte waarop 'n kunstenaar was eerder as hul algehele aantal strome.

Slae per minuut

Watter snit het die hoogste BPM?

 qa.invoke({"query": "Which track has the highest BPM?"}) > Entering new GraphCypherQAChain chain... Generated Cypher: cypher MATCH (t:Track) RETURN t ORDER BY t.bpm DESC LIMIT 1 Full Context: [{'t': {'id': 'seven-feat-latto-explicit-ver--2023'}}] > Finished chain. { "query": "Which track has the highest BPM?", "result": "I don't know the answer." }

Verbetering van die Cypher Generation Prompt

In hierdie geval lyk die Cypher goed en die korrekte resultaat is by die prompt ingesluit, maar gpt-4o kon nie die antwoord interpreteer nie. Dit lyk of die CYPHER_GENERATION_PROMPT wat aan die GraphCypherQACain oorgedra is, kan doen met bykomende instruksies om die kolomname meer breedvoerig te maak.

Gebruik altyd verbose kolomname in die Cypher-stelling deur die etiket- en eiendomsname te gebruik. Gebruik byvoorbeeld 'persoonnaam' in plaas van 'naam'.

GraphCypherQACain met pasgemaakte prompt:

 CYPHER_GENERATION_TEMPLATE = """Task:Generate Cypher statement to query a graph database. Instructions: Use only the provided relationship types and properties in the schema. Do not use any other relationship types or properties that are not provided. Schema: {schema} Note: Do not include any explanations or apologies in your responses. Do not respond to any questions that might ask anything else than for you to construct a Cypher statement. Do not include any text except the generated Cypher statement. Always use verbose column names in the Cypher statement using the label and property names. For example, use 'person_name' instead of 'name'. Include data from the immediate network around the node in the result to provide extra context. For example, include the Movie release year, a list of actors and their roles, or the director of a movie. When ordering by a property, add an `IS NOT NULL` check to ensure that only nodes with that property are returned. Examples: Here are a few examples of generated Cypher statements for particular questions: # How many people acted in Top Gun? MATCH (m:Movie {{name:"Top Gun"}}) RETURN COUNT { (m)<-[:ACTED_IN]-() } AS numberOfActors The question is: {question}""" CYPHER_GENERATION_PROMPT = PromptTemplate( input_variables=["schema", "question"], template=CYPHER_GENERATION_TEMPLATE ) qa = GraphCypherQAChain.from_llm( llm, graph=graph, allow_dangerous_requests=True, verbose=True, cypher_prompt=CYPHER_GENERATION_PROMPT, )

Snitte uitgevoer deur die meeste kunstenaars

Grafieke is uitstekend om 'n telling van die aantal verwantskappe volgens tipe en rigting terug te gee.

 qa.invoke({"query": "Which tracks are performed by the most artists?"}) > Entering new GraphCypherQAChain chain... Generated Cypher: cypher MATCH (t:Track) WITH t, COUNT { (t)-[:PERFORMED_BY]->(:Artist) } as artist_count WHERE artist_count IS NOT NULL RETURN t.id AS track_id, t.name AS track_name, artist_count ORDER BY artist_count DESC Full Context: [{'track_id': 'los-del-espacio-2023', 'track_name': 'Los del Espacio', 'artist_count': 8}, {'track_id': 'se-le-ve-2021', 'track_name': 'Se Le Ve', 'artist_count': 8}, {'track_id': 'we-don-t-talk-about-bruno-2021', 'track_name': "We Don't Talk About Bruno", 'artist_count': 7}, {'track_id': 'cayï-ï-la-noche-feat-cruz-cafunï-ï-abhir-hathi-bejo-el-ima--2022', 'track_name': None, 'artist_count': 6}, {'track_id': 'jhoome-jo-pathaan-2022', 'track_name': 'Jhoome Jo Pathaan', 'artist_count': 6}, {'track_id': 'besharam-rang-from-pathaan--2022', 'track_name': None, 'artist_count': 6}, {'track_id': 'nobody-like-u-from-turning-red--2022', 'track_name': None, 'artist_count': 6}, {'track_id': 'ultra-solo-remix-2022', 'track_name': 'ULTRA SOLO REMIX', 'artist_count': 5}, {'track_id': 'angel-pt-1-feat-jimin-of-bts-jvke-muni-long--2023', 'track_name': None, 'artist_count': 5}, {'track_id': 'link-up-metro-boomin-don-toliver-wizkid-feat-beam-toian-spider-verse-remix-spider-man-across-the-spider-verse--2023', 'track_name': None, 'artist_count': 5}] > Finished chain. { "query": "Which tracks are performed by the most artists?", "result": "The tracks \"Los del Espacio\" and \"Se Le Ve\" are performed by the most artists, with each track having 8 artists." }

Opsomming

Die CSV-analise en modellering is die mees tyd-intensiewe deel. Dit kan meer as vyf minute neem om te genereer.

Die koste self was redelik goedkoop. In agt uur se eksperimentering moes ek honderde versoeke gestuur het en ek het uiteindelik 'n dollar of so spandeer.

Daar was 'n aantal uitdagings om tot hierdie punt te kom:

• Die opdragte het verskeie herhalings geneem om reg te kom. Hierdie probleem kan oorkom word deur die model fyn in te stel of voorbeelde van 'n paar skoot te verskaf.
• JSON-antwoorde vanaf GPT-4o kan inkonsekwent wees. Ek is aanbeveel json-repair , wat beter was as om die LLM te probeer kry om sy eie JSON-uitset te valideer.

Ek kan sien dat hierdie benadering goed werk in 'n LangGraph-implementering waar die bedrywighede in volgorde uitgevoer word, wat 'n LLM die vermoë gee om die model te bou en te verfyn. Soos nuwe modelle vrygestel word, kan hulle ook baat vind by fynverstelling.

Kom meer te wete

Kyk na die gebruik van groot taalmodelle met Neo4j vir meer inligting oor die vaartbelyning van die proses van die skep van kennisgrafieke met LLM's. Lees Skep 'n Neo4j GraphRAG-werkvloei deur LangChain en LangGraph te gebruik vir meer oor LangGraph en Neo4j. En om meer te wete te kom oor fyninstelling, kyk na Knowledge Graphs and LLMs: Fine-Tuning vs. Retrieval-Augmented Generation .

Om meer oor hierdie onderwerp te wete te kom, sluit by ons aan by NODES 2024 op 7 November, ons gratis virtuele ontwikkelaarkonferensie oor intelligente toepassings, kennisgrafieke en KI. Registreer nou!