CSV-tiedostojen muuntaminen kaavioiksi LLM:ien avulla: Vaiheittainen opas

Miten LLM:t menestyvät yrittäessään luoda kaavioita litteistä CSV-tiedostoista?

Suuri osa työstäni on Neo4j:n käyttökokemusten parantaminen. Usein tiedon saaminen Neo4j:hen ja sen tehokas mallintaminen on keskeinen haaste käyttäjille, varsinkin alkuaikoina. Vaikka alkuperäinen tietomalli on tärkeä ja vaatii harkintaa, se voidaan helposti muuttaa suorituskyvyn parantamiseksi tiedon koon tai käyttäjien määrän kasvaessa.

Joten haasteena itselleni ajattelin katsovani, voisiko LLM auttaa alkuperäisen tietomallin kanssa. Jos ei muuta, se osoittaisi, miten asiat liittyvät toisiinsa, ja tarjoaisi käyttäjälle nopeita tuloksia, joita he voivat näyttää muille.

Intuitiivisesti tiedän, että tietojen mallintaminen on iteratiivinen prosessi, ja suuret tietomäärät voivat helposti häiritä tiettyjä LLM:itä, joten tämä tarjosi hyvän tilaisuuden käyttää LangGraphia työskennelläksesi jaksoittain datan läpi.

Sukellaanpa kehotteisiin, joiden ansiosta se tapahtui.

Graafimallinnuksen perusteet

Graph Data Modeling Fundamentals -kurssi GraphAcademyssa opastaa sinut kaavion tietojen mallintamisen perusteisiin, mutta ensimmäiseksi käytän seuraavia nyrkkisääntöjä:

• Substantiivit muuttuvat tunnisteiksi – Ne kuvaavat asiaa , jota solmu edustaa.
• Verbeistä tulee suhdetyyppejä – Ne kuvaavat, miten asiat liittyvät toisiinsa.
• Kaikesta muusta tulee ominaisuuksia (erityisesti adverbeja) — Sinulla on nimi ja voit ajaa harmaalla autolla.

Verbit voivat olla myös solmuja; saatat olla iloinen, kun tietää, että henkilö on tilannut tuotteen, mutta perusmallin perusteella ei voi tietää, missä ja milloin tuote on tilattu. Tässä tapauksessa järjestyksestä tulee mallin uusi solmu.

Olen varma, että tämä voitaisiin tislata kehotteeksi luoda nollakuvausmenetelmä graafisen tiedon mallintamiseen.

Iteratiivinen lähestymistapa

Yritin tätä lyhyesti muutama kuukausi sitten ja huomasin, että käyttämäni malli hajaantui helposti käsiteltäessä suurempia skeemoja, ja kehotteet saavuttivat melko nopeasti LLM:n token-rajat.

Ajattelin kokeilla iteratiivista lähestymistapaa tällä kertaa ja ottaa avaimet yksi kerrallaan. Tämän pitäisi auttaa välttämään häiriötekijöitä, koska LLM:n tarvitsee ottaa huomioon vain yksi kohde kerrallaan.

Lopullinen lähestymistapa käytti seuraavia vaiheita:

1. Lataa CSV-tiedosto Pandas-tietokehykseen.
2. Analysoi jokainen CSV:n sarake ja liitä se tietomalliin löyhästi JSON-skeemaan.
3. Tunnista ja lisää puuttuvat yksilölliset tunnukset jokaiselle entiteetille.
4. Tarkista tietomallin tarkkuus.
5. Luo Cypher-käskyt solmujen ja suhteiden tuomiseksi.
6. Luo yksilölliset rajoitukset, jotka tukevat tuontilausekkeita.
7. Luo rajoitukset ja suorita tuonti.

Tiedot

Katsoin Kagglesta nopeasti mielenkiintoisen tietojoukon . Tietojoukko, joka erottui, oli Spotify 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 riviä × 25 saraketta

Se on suhteellisen yksinkertainen, mutta huomaan heti, että kappaleiden ja artistien välillä pitäisi olla suhteita.

Tietojen puhtaushaasteita on myös voitettava, koska sarakkeiden nimet ja artistit ovat pilkuilla erotettuja arvoja artist(s)_name-sarakkeessa.

LLM:n valinta

Halusin todella käyttää paikallista LLM:ää tähän, mutta huomasin varhain, että Llama 3 ei leikkaa sitä. Jos olet epävarma, käytä OpenAI:ta:

 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")

Tietomallin luominen

Käytin lyhennettyä mallinnusohjeiden sarjaa tietojen mallinnuskehotteen luomiseen. Minun piti muokata kehotetta muutaman kerran saadakseni tasaisen tulosteen.

Nollakuvan esimerkki toimi suhteellisen hyvin, mutta huomasin, että tulos oli epäjohdonmukainen. Strukturoidun lähdön määrittäminen JSON-lähdön säilyttämiseksi auttoi todella:

 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")

Muutaman laukauksen esimerkkitulostus

Itse JSON oli myös epäjohdonmukainen, joten päädyin määrittämään skeeman elokuvasuositusten tietojoukon perusteella.

Esimerkkituloste:

 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"]), ], ), ]

Minun piti poiketa tiukasta JSON-skeemasta ja lisätä tuotteeseen sarakkeen_nimi-kenttä auttaakseni LLM:ää luomaan tuontiskriptin. Kuvausesimerkkien antaminen auttoi myös tässä, muuten MATCH-lauseessa käytetyt ominaisuudet olivat epäjohdonmukaisia.

Ketju

Tässä viimeinen kehotus:

 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)

Ketjun toteuttaminen

Mallin iteratiivista päivittämistä varten iteroin tietokehyksen avaimet ja välitin jokaisen avaimen, sen tietotyypin ja viisi ensimmäistä yksilöllistä arvoa kehotteeseen:

 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

Konsolin lähtö:

 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']

Muutaman korjauksen jälkeen kehotteeseen käsitellä käyttötapauksia, päädyin malliin, johon olin melko tyytyväinen. LLM oli onnistunut määrittämään, että tietojoukko koostui kappaleesta, esittäjästä ja PERFORMED_BY-suhteesta yhdistääkseen nämä kaksi:

 [ { "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"], }, ], }, ]

Yksilöllisten tunnisteiden lisääminen

Huomasin, että skeema ei sisältänyt yksilöllisiä tunnisteita, ja tämä voi muodostua ongelmaksi suhteiden tuonnissa. On selvää, että eri artistit julkaisevat kappaleita samalla nimellä ja kahdella artistilla voi olla sama nimi.

Tästä syystä oli tärkeää luoda kappaleille tunniste, jotta ne voidaan erottaa suuremmasta tietojoukosta:

 # 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)

Tämä vaihe on todella pakollinen vain solmuille, joten poimin solmut skeemasta, suoritin ketjun kullekin ja yhdistän sitten suhteet päivitettyihin määritelmiin:

 # 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

Tietomallin tarkistus

Järkevyyden vuoksi kannattaa tarkistaa mallin optimoinnit. Model_prompt teki hyvää työtä substantiivien ja verbien tunnistamisessa, mutta monimutkaisemmassa mallissa.

Yksi iteraatio käsitteli *_playlists- ja _charts-sarakkeet tunnuksina ja yritti luoda Stream-solmuja ja IN_PLAYLIST-suhteita. Oletan, että tämä johtui yli 1 000:n määrästä, mukaan lukien muotoilu pilkulla (esim. 1 001).

Hyvä idea, mutta ehkä vähän liian fiksu. Mutta tämä osoittaa, kuinka tärkeää on, että silmukassa on ihminen, joka ymmärtää tietorakenteen.

 # 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

Tosimaailmassa haluaisin suorittaa tämän muutaman kerran parantaakseni tietomallia iteratiivisesti. Laittaisin enimmäisrajan ja toistaisin sitten siihen pisteeseen asti tai tietomalliobjekti ei enää muutu.

Luo tuontilausunnot

Tähän mennessä skeeman pitäisi olla riittävän vankka ja sisältää mahdollisimman paljon tietoa, jotta LLM voi luoda joukon tuontiskriptejä.

Neo4j:n tietojen tuontisuositusten mukaisesti tiedosto tulee käsitellä useita kertoja ja joka kerta tuoda yksi solmu tai suhde, jotta vältetään innokkaat toiminnot ja lukitseminen.

 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} """)

Tämä ketju vaatii eri tulosobjektin kuin edelliset vaiheet. Tässä tapauksessa cypher-jäsen on tärkein, mutta halusin sisällyttää mukaan myös chain_of_thought-avaimen kannustamaan ajatusketjua:

 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)

Sama prosessi koskee sitten jokaisen tarkistetun määritelmän iterointia ja Cypherin luomista:

 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)

Konsolin lähtö:

 ------ 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)

Tämä kehotus vaati jonkin verran suunnittelua johdonmukaisten tulosten saavuttamiseksi:

• Joskus Cypher sisältäisi MERGE-käskyn, jossa on useita määriteltyjä kenttiä, mikä on parhaimmillaan epäoptimaalista. Jos jokin sarakkeista on nolla, koko tuonti epäonnistuu.
• Joskus tuloksena oli apoc.period.iterate , jota ei enää tarvita, ja halusin koodin, jonka voisin suorittaa Python-ohjaimella.
• Minun piti toistaa, että määritettyä sarakkeen nimeä tulisi käyttää suhteita luotaessa.
• LLM ei vain noudattanut ohjeita käytettäessä yksilöllistä tunnistetta suhteen kummassakin päässä olevissa solmuissa, joten kesti muutaman yrityksen saada se noudattamaan kuvauksen ohjeita. Tämän kehotteen ja model_prompt-kehotteen välillä oli edestakaisin.
• Erikoismerkkejä (esim. energia_%) sisältäviin sarakkeiden nimiin tarvittiin selkämerkinnät.

Olisi myös hyödyllistä jakaa tämä kahteen kehotteeseen - yksi solmuja ja toinen suhteita varten. Mutta se on toisen päivän tehtävä.

Luo ainutlaatuiset rajoitukset

Seuraavaksi tuontiskriptejä voidaan käyttää perustana ainutlaatuisten rajoitusten luomiseen tietokantaan:

 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)

Konsolin lähtö:

 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

Joskus tämä kehote palauttaa lausekkeita indekseille ja rajoituksille, mikä tarkoittaa puolipisteen jakoa.

Suorita tuonti

Kun kaikki oli paikallaan, oli aika suorittaa Cypher-lauseet:

 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 tietojoukossa

Tämä viesti ei olisi täydellinen ilman datajoukon laadunvarmistusta GraphCypherQAChainin avulla:

 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 )

Suosituimmat artistit

Ketkä ovat tietokannan suosituimmat artistit?

 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." }

LLM näytti arvioivan suosiota artistin kappaleiden lukumäärän perusteella, eikä niiden kokonaismäärän perusteella.

lyöntiä minuutissa

Millä kappaleella on korkein 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." }

Cypher Generation Prompt -kehotteen parantaminen

Tässä tapauksessa Cypher näyttää hyvältä ja oikea tulos sisällytettiin kehotteeseen, mutta gpt-4o ei voinut tulkita vastausta. Näyttää siltä, että GraphCypherQAChainille välitetty CYPHER_GENERATION_PROMPT voisi tehdä lisäohjeista tehdäkseen sarakkeiden nimistä monisanaisempia.

Käytä aina monisanaisia sarakkeiden nimiä Cypher-käskyssä käyttämällä tunnisteen ja ominaisuuksien nimiä. Käytä esimerkiksi 'henkilön_nimi' nimen sijaan.

GraphCypherQAChain mukautetulla kehotteella:

 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, )

Useimpien artistien esittämät kappaleet

Kaaviot loistavat palauttamaan suhteiden lukumäärän tyypin ja suunnan mukaan.

 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." }

Yhteenveto

CSV-analyysi ja mallintaminen on aikaa vievin osa. Sen luominen voi kestää yli viisi minuuttia.

Kustannukset sinänsä olivat melko halpoja. Kahdeksan tunnin kokeilun aikana olen lähettänyt satoja pyyntöjä ja päädyin käyttämään noin dollarin.

Tähän pisteeseen pääsemiseksi oli useita haasteita:

• Kehotteet veivät useita iteraatioita, jotta ne menivät oikein. Tämä ongelma voitaisiin ratkaista hienosäätämällä mallia tai antamalla muutamia esimerkkejä.
• GPT-4o:n JSON-vastaukset voivat olla epäjohdonmukaisia. Minulle suositeltiin json-repairia , mikä oli parempi kuin yrittää saada LLM vahvistamaan oman JSON-tulostuksensa.

Näen tämän lähestymistavan toimivan hyvin LangGraph-toteutuksessa, jossa toiminnot suoritetaan peräkkäin, mikä antaa LLM:lle mahdollisuuden rakentaa ja tarkentaa mallia. Kun uusia malleja julkaistaan, ne voivat myös hyötyä hienosäädöstä.

Lisätietoja

Tutustu suurten kielimallien valjastamiseen Neo4j:n avulla saadaksesi lisätietoja tietograafin luontiprosessin virtaviivaistamisesta LLM:ien avulla. Lue Neo4j GraphRAG -työnkulun luominen LangChainilla ja LangGraphilla saadaksesi lisätietoja LangGraphista ja Neo4j:stä. Ja saadaksesi lisätietoja hienosäädöstä, tutustu Knowledge Graphs and LLMs: Fine-tuning vs. Retrieval-Augmented Generation -artikkeliin .

Saat lisätietoja tästä aiheesta liittymällä NODES 2024 -tapahtumaan 7. marraskuuta, ilmaiseen virtuaaliseen kehittäjäkonferenssiimme älykkäistä sovelluksista, tietokaavioista ja tekoälystä. Rekisteröidy nyt!