Transfòme Fichye CSV nan Grafik ak LLMs: Yon Gid Etap-pa-Etap

Ki jan LLM yo ye lè y ap eseye kreye graf nan dosye CSV plat? Yon gwo pati nan travay mwen se amelyore eksperyans itilizatè yo ak Neo4j. Souvan, jwenn done nan Neo4j ak modèl li avèk efikasite se yon defi kle pou itilizatè yo, espesyalman nan premye jou yo. Malgre ke modèl done inisyal la enpòtan epi li bezwen meditasyon, li ka fasilman refactorize pou amelyore pèfòmans pandan gwosè done oswa kantite itilizatè yo ap grandi. Se konsa, kòm yon defi pou tèt mwen, mwen te panse mwen ta wè si yon LLM ta ka ede ak modèl done inisyal la. Si pa gen anyen lòt bagay, li ta demontre kijan yo konekte epi bay itilizatè a kèk rezilta rapid yo ka montre lòt moun. bagay Entwisyon, mwen konnen modèl done se yon pwosesis iteratif, ak sèten LLM yo ka fasil distrè pa gwo kantite done, kidonk sa a te prezante yon bon opòtinite pou itilize pou travay nan sik atravè done yo. LangGraph Ann plonje nan envit yo ki te fè li rive. Prensip Fondamantal Modèl graf gide w nan baz modèl done yo nan yon graf, men kòm premye pas, mwen itilize règ sa yo: Graph Data Modeling Fundamentals kou sou GraphAcademy Non yo vin etikèt — Yo dekri ke ne la reprezante. bagay Vèb yo vin kalite relasyon — Yo dekri kijan yo konekte. bagay Tout lòt bagay vin pwopriyete (patikilyèman advèb) — Ou gen yon non epi ou ka kondwi yon machin gri. Vèb yo kapab tou nœuds; ou ka kontan konnen ke yon te yon men modèl debaz sa a pa pèmèt ou konnen ki kote ak ki lè pwodwi a te kòmande. Nan ka sa a, lòd vin tounen yon nouvo ne nan modèl la. moun kòmande pwodwi, Mwen sèten sa a ta ka distile nan yon èd memwa pou kreye yon apwòch zewo-piki nan modèl done graf. Yon Apwòch Iteratif Mwen te eseye sa a yon ti tan kèk mwa de sa epi mwen te jwenn ke modèl mwen te itilize a te vin fasil distrè lè yo te fè fas ak pi gwo chema, ak envit yo byen vit rive nan limit siy LLM la. Mwen te panse mwen ta eseye yon apwòch iteratif fwa sa a, pran kle yo youn nan yon tan. Sa a ta dwe ede evite distraksyon paske LLM a sèlman bezwen konsidere yon atik nan yon moman. Apwòch final la te itilize etap sa yo: Chaje dosye CSV la nan yon panda dataframe. Analize chak kolòn nan CSV a epi ajoute li nan yon modèl done ki baze sou JSON Schema. Idantifye epi ajoute ID inik ki manke pou chak antite. Revize modèl done a pou presizyon. Jenere deklarasyon Cypher pou enpòte nœuds yo ak relasyon yo. Jenere kontrent inik ki soutni deklarasyon enpòte yo. Kreye kontrent yo epi kouri enpòte a. Done yo Mwen te pran yon gade rapid sou Kaggle pou yon . Ansanm done ki te kanpe deyò se te . seri done enteresan 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 ranje × 25 kolòn Li relativman senp, men mwen ka wè imedyatman ke ta dwe gen relasyon ant tracks ak atis. Genyen tou defi pou pwòpte done yo simonte, an tèm de non kolòn ak atis yo se valè ki separe ak vigil nan kolòn artist(s)_name. Chwazi yon LLM Mwen reyèlman te vle sèvi ak yon LLM lokal pou sa a, men mwen te dekouvri byen bonè ke Llama 3 pa ta koupe li. Si w gen dout, retounen sou 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") Kreye yon modèl done Mwen te itilize yon seri abreje nan enstriksyon modèl yo kreye èd memwa a modèl done. Mwen te oblije enjenyè èd memwa a kèk fwa pou jwenn yon pwodiksyon ki konsistan. Egzanp zewo-piki a te travay relativman byen, men mwen te jwenn ke pwodiksyon an te konsistan. Defini yon pwodiksyon estriktire pou kenbe pwodiksyon JSON la vrèman ede: 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") Sòti Egzanp kèk-piki JSON nan tèt li te konsistan tou, kidonk mwen te fini defini yon chema ki baze sou seri done rekòmandasyon fim yo. Egzanp pwodiksyon: 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"]), ], ), ] Mwen te oblije devye de Schema JSON strik epi ajoute jaden column_name nan pwodiksyon an pou ede LLM jenere script enpòte a. Bay egzanp deskripsyon tou te ede nan sans sa a, otreman pwopriyete yo te itilize nan kloz MATCH la te konsistan. Chèn nan Men èd memwa final la: 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) Egzekite chèn lan Pou iteratif mete ajou modèl la, mwen repete sou kle yo nan dataframe a epi yo pase chak kle, kalite done li yo, ak senk premye valè inik yo nan èd memwa a: 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 Pwodiksyon konsole: 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'] Apre kèk ajisteman nan èd memwa a okipe ka itilize, mwen te fini ak yon modèl mwen te byen kontan ak. LLM a te jere detèmine ke seri done a te konpoze de Track, Atis, ak yon relasyon PERFORMED_BY konekte de sa yo: [ { "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"], }, ], }, ] Ajoute Idantifyan inik Mwen remake ke chema a pa t gen okenn idantifyan inik, e sa ka vin yon pwoblèm lè li rive enpòte relasyon. Li vle di ke ak de atis ka gen menm non. atis diferan ta lage chante ak menm non Pou rezon sa a, li te enpòtan yo kreye yon idantifyan pou Tracks pou yo ka diferansye nan yon seri done ki pi gwo: # 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) Etap sa a se sèlman reyèlman obligatwa pou nœuds, kidonk mwen ekstrè nœuds yo soti nan chema a, kouri chèn lan pou chak ak Lè sa a, konbine relasyon yo ak definisyon yo mete ajou: # 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 Revizyon Modèl Done Pou saniti, li vo tcheke modèl la pou optimize. Model_prompt la te fè yon bon travay nan idantifye non yo ak vèb yo, men nan yon modèl ki pi konplèks. Yon iterasyon te trete kolòn *_playlists ak _charts yo kòm ID epi li te eseye kreye nœuds Stream ak relasyon IN_PLAYLIST. Mwen sipoze sa a te akòz konte a plis pase 1,000 ki gen ladan fòma ak yon vigil (egzanp, 1,001). Bèl lide, men petèt yon ti kras twò entelijan. Men, sa montre enpòtans pou gen yon moun nan bouk la ki konprann estrikti done yo. # 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 Nan yon senaryo nan mond reyèl la, mwen ta vle kouri sa a yon kèk fwa amelyore iterativman modèl done a. Mwen ta mete yon limit maksimòm, Lè sa a, repete jiska pwen sa a oswa objè a modèl done pa chanje ankò. Jenere Deklarasyon Enpòte Nan pwen sa a, chema a ta dwe solid ase epi gen ladan enfòmasyon otank posib pou pèmèt yon LLM jenere yon seri scripts enpòte. Nan liy ak , yo ta dwe trete dosye a plizyè fwa, chak fwa enpòte yon sèl ne oswa relasyon pou fè pou evite operasyon anvi ak bloke. rekòmandasyon Neo4j done enpòte 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} """) Chèn sa a mande pou yon objè pwodiksyon diferan ak etap anvan yo. Nan ka sa a, manm chifreman an pi enpòtan, men mwen te vle tou mete yon kle chain_of_thought pou ankouraje Chain of Thought: 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) Lè sa a, menm pwosesis la aplike pou repete sou chak definisyon yo revize epi jenere Cypher la: 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) Pwodiksyon konsole: ------ 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) Èd memwa sa a te pran kèk jeni pou reyalize rezilta konsistan: Pafwa Cypher a ta gen ladan deklarasyon MERGE ak plizyè jaden defini, ki pa pi bon nan pi bon. Si nenpòt nan kolòn yo nil, tout enpòte a ap echwe. Pafwa, rezilta a ta gen ladan , ki pa nesesè ankò, epi mwen te vle kòd mwen te kapab egzekite ak chofè a Python. apoc.period.iterate Mwen te oblije repete ke yo ta dwe itilize non kolòn espesifye lè yo kreye relasyon yo. LLM a jis pa ta swiv enstriksyon yo lè w ap itilize idantifyan inik sou nœuds yo nan chak fen nan relasyon an, kidonk sa te pran kèk tantativ pou jwenn li swiv enstriksyon yo nan deskripsyon an. Te gen kèk retounen ak lide ant èd memwa sa a ak model_prompt la. Backticks yo te bezwen pou non kolòn yo ki te gen karaktè espesyal (egzanp enèji_%). Li ta tou benefisye divize sa a an de envit - youn pou nœuds ak youn pou relasyon yo. Men, sa se yon travay pou yon lòt jou. Kreye kontrent inik yo Apre sa, scripts enpòte yo ka itilize kòm yon baz pou kreye kontrent inik nan baz done a: 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) Pwodiksyon konsole: 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 Pafwa èd memwa sa a ta retounen deklarasyon pou endèks ak kontrent, alò fann nan semi-kolo a. Kouri Import a Avèk tout bagay an plas, li te tan pou egzekite deklarasyon Cypher: 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 sou Dataset la Pòs sa a pa ta konplè san kèk QA sou dataset la lè l sèvi avèk GraphCypherQACchain: 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 ) Atis ki pi popilè Ki moun ki atis ki pi popilè nan baz done a? 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 a te sanble yo jije popilarite an tèm de kantite tren yon atis te sou olye ke kantite jeneral yo nan kouran. Bat pou chak minit Ki tras ki gen BPM ki pi wo a? 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." } Amelyore Cypher Generation Prompt Nan ka sa a, Cypher a sanble byen epi rezilta kòrèk la te enkli nan èd memwa a men gpt-4o pa t 'kapab entèprete repons lan. Li sanble ke CYPHER_GENERATION_PROMPT yo te pase nan GraphCypherQACchain a ta ka fè ak enstriksyon adisyonèl pou fè non kolòn yo plis detay. Toujou sèvi ak non kolòn pwolib nan deklarasyon an Cypher lè l sèvi avèk etikèt la ak non pwopriyete. Pa egzanp, sèvi ak 'person_name' olye de 'non'. GraphCypherQACain ak èd memwa koutim: 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, ) Tracks ki fèt pa pi fò atis yo Graf yo briye nan retounen yon konte kantite relasyon pa kalite ak direksyon. 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." } Rezime Analiz CSV ak modèl se pati ki pi entansif nan tan. Li ta ka pran plis pase senk minit pou jenere. Depans yo tèt yo te trè bon mache. Nan uit èdtan nan eksperimantasyon, mwen dwe te voye dè santèn de demann epi mwen te fini depanse yon dola oswa konsa. Te gen yon kantite defi pou rive nan pwen sa a: Envit yo te pran plizyè iterasyon pou jwenn dwa. Pwoblèm sa a ta ka simonte pa amann modèl la oswa bay egzanp kèk-piki. Repons JSON ki soti nan GPT-4o ka enkonsistan. Mwen te rekòmande , ki te pi bon pase eseye jwenn LLM a valide pwodiksyon JSON pwòp li yo. json-repair Mwen ka wè apwòch sa a ap travay byen nan yon aplikasyon LangGraph kote operasyon yo ap kouri nan sekans, bay yon LLM kapasite nan bati ak rafine modèl la. Kòm nouvo modèl yo lage, yo ka benefisye tou de amann-akor. Aprann Plis Tcheke pou plis enfòmasyon sou rasyonalize pwosesis kreyasyon graf konesans ak LLM yo. Li pou plis enfòmasyon sou LangGraph ak Neo4j. Epi pou w aprann plis sou ajisteman amann, tcheke . Harnessing Large Language Models With Neo4j Kreye yon workflow Neo4j GraphRAG Sèvi ak LangChain ak LangGraph Grafik Konesans ak LLM: Fine-Tuning vs. Retrieval-Augmented Generation Imaj Karakteristik: Modèl graf montre Tracks ak relasyon PERFORMED_BY ak Atis yo. Foto pa otè a. Pou aprann plis sou sijè sa a, vin jwenn nou nan NODES 2024 le 7 novanm, konferans gratis pwomotè vityèl nou an sou aplikasyon entèlijan, graf konesans, ak AI. Enskri kounye a!