paint-brush
LLM को साथ CSV फाइलहरूलाई ग्राफमा रूपान्तरण गर्दै: एक चरण-दर-चरण गाइडद्वारा@neo4j
नयाँ इतिहास

LLM को साथ CSV फाइलहरूलाई ग्राफमा रूपान्तरण गर्दै: एक चरण-दर-चरण गाइड

द्वारा Neo4j41m2024/10/29
Read on Terminal Reader

धेरै लामो; पढ्नकाे लागि

CSV फाइलहरूलाई ग्राफ संरचनाहरूमा रूपान्तरण गर्न LLMs प्रयोग गरी अन्वेषण गर्नुहोस्, Neo4j मा डेटा मोडलिङलाई पुनरावृत्ति, प्रम्प्ट-आधारित दृष्टिकोणको साथ सुधार गर्नुहोस्।
featured image - LLM को साथ CSV फाइलहरूलाई ग्राफमा रूपान्तरण गर्दै: एक चरण-दर-चरण गाइड
Neo4j HackerNoon profile picture
0-item
1-item


फ्ल्याट CSV फाइलहरूबाट ग्राफहरू सिर्जना गर्ने प्रयास गर्दा LLM ले कसरी भाडामा लिन्छ?

मेरो कामको ठूलो हिस्सा Neo4j को साथ प्रयोगकर्ताहरूको अनुभव सुधार गर्नु हो। अक्सर, Neo4j मा डेटा प्राप्त गर्नु र यसलाई कुशलतापूर्वक मोडेल गर्नु प्रयोगकर्ताहरूका लागि विशेष चुनौती हो, विशेष गरी प्रारम्भिक दिनहरूमा। यद्यपि प्रारम्भिक डेटा मोडेल महत्त्वपूर्ण छ र विचार गर्न आवश्यक छ, डेटा आकार वा प्रयोगकर्ताहरूको संख्या बढ्दै जाँदा कार्यसम्पादन सुधार गर्न यसलाई सजिलैसँग रिफ्याक्टर गर्न सकिन्छ।


त्यसोभए, आफैलाई चुनौतीको रूपमा, मैले सोचें कि LLM ले प्रारम्भिक डेटा मोडेलमा मद्दत गर्न सक्छ कि भनेर हेर्नेछु। यदि अरू केहि छैन भने, यसले चीजहरू कसरी जडान भएका छन् भनेर देखाउनेछ र प्रयोगकर्तालाई उनीहरूले अरूलाई देखाउन सक्ने केही द्रुत परिणामहरू प्रदान गर्दछ।


सहज रूपमा, मलाई थाहा छ डाटा मोडलिङ एक पुनरावृत्ति प्रक्रिया हो, र निश्चित LLM हरू सजिलैसँग ठूलो मात्रामा डेटाबाट विचलित हुन सक्छन्, त्यसैले यसले डेटा मार्फत चक्रहरूमा काम गर्न LangGraph प्रयोग गर्ने राम्रो अवसर प्रस्तुत गर्‍यो।


आउनुहोस् प्रम्प्टहरूमा डुबौं जसले यो भयो।

ग्राफ मोडलिङको आधारभूत कुराहरू

GraphAcademy मा ग्राफ डेटा मोडलिङ आधारभूत पाठ्यक्रमले तपाईंलाई ग्राफमा मोडलिङ डेटाको आधारभूत कुराहरू मार्फत मार्गदर्शन गर्दछ, तर पहिलो पासको रूपमा, म निम्न थम्ब नियमहरू प्रयोग गर्छु:


  • संज्ञाहरू लेबल बन्छन् - तिनीहरूले नोडले प्रतिनिधित्व गर्ने कुराको वर्णन गर्छन्।
  • क्रियाहरू सम्बन्ध प्रकारहरू हुन्छन् - तिनीहरूले चीजहरू कसरी जोडिएका छन् भनेर वर्णन गर्छन्।
  • अरू सबै गुणहरू बन्छ (विशेष गरी क्रियाविशेषण) — तपाईंको नाम छ र खैरो कार चलाउन सक्छ।


क्रियाहरू नोडहरू पनि हुन सक्छन्; तपाईलाई थाहा छ कि एक व्यक्तिले उत्पादन अर्डर गरेको, तर त्यो आधारभूत मोडेलले तपाईलाई उत्पादन कहाँ र कहिले अर्डर गरिएको थियो भनेर जान्न अनुमति दिँदैन। यस अवस्थामा, अर्डर मोडेलमा नयाँ नोड हुन्छ।


म पक्का छु कि यो ग्राफ डेटा मोडलिङमा शून्य-शट दृष्टिकोण सिर्जना गर्न प्रम्प्टमा डिस्टिल्ड गर्न सकिन्छ।

एक पुनरावृत्ति दृष्टिकोण

मैले केहि महिना पहिले यो प्रयास गरेको थिएँ र मैले प्रयोग गरिरहेको मोडेल ठूला योजनाहरूसँग व्यवहार गर्दा सजिलै विचलित भएको फेला पारे, र प्रम्प्टहरू चाँडै LLM को टोकन सीमामा पुगे।


मैले सोचे कि म यस पटक पुनरावृत्तिको प्रयास गर्छु, कुञ्जीहरू एक पटकमा लिएर। यसले व्याकुलताबाट बच्न मद्दत गर्नुपर्छ किनभने LLM ले एक पटकमा एउटा वस्तुलाई मात्र विचार गर्नुपर्छ।


अन्तिम दृष्टिकोणले निम्न चरणहरू प्रयोग गर्यो:


  1. CSV फाइललाई Pandas डेटाफ्रेममा लोड गर्नुहोस्।
  2. CSV मा प्रत्येक स्तम्भको विश्लेषण गर्नुहोस् र JSON स्कीमामा आधारित डेटा मोडेलमा जोड्नुहोस्।
  3. प्रत्येक एकाइको लागि छुटेको अद्वितीय आईडीहरू पहिचान गर्नुहोस् र थप्नुहोस्।
  4. सटीकताको लागि डाटा मोडेल समीक्षा गर्नुहोस्।
  5. नोडहरू र सम्बन्धहरू आयात गर्न साइफर स्टेटमेन्टहरू उत्पन्न गर्नुहोस्।
  6. आयात कथनहरूलाई अन्डरपिन गर्ने अद्वितीय अवरोधहरू उत्पन्न गर्नुहोस्।
  7. बाधाहरू सिर्जना गर्नुहोस् र आयात चलाउनुहोस्।

डाटा

मैले एक चाखलाग्दो डेटासेटको लागि Kaggle मा एक द्रुत नजर लिएँ। बाहिर खडा भएको डेटासेट Spotify सबैभन्दा स्ट्रिम गरिएका गीतहरू थिए।


 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 पङ्क्तिहरू × 25 स्तम्भहरू


यो अपेक्षाकृत सरल छ, तर म सिधै देख्न सक्छु कि ट्र्याक र कलाकारहरू बीच सम्बन्ध हुनुपर्छ।


स्तम्भ नामहरू र कलाकारहरू कलाकार(हरू)_नाम स्तम्भ भित्र अल्पविराम-विभाजित मानहरूको सन्दर्भमा डेटा सफाई चुनौतीहरू पनि छन्।

LLM छनौट गर्दै

म साँच्चै यसको लागि स्थानीय LLM प्रयोग गर्न चाहन्थे, तर मैले चाँडै थाहा पाएँ कि Llama 3 ले यसलाई काट्दैन। यदि शंकामा, OpenAI मा फर्कनुहोस्:


 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")

डाटा मोडेल सिर्जना गर्दै

मैले डेटा मोडलिङ प्रम्प्ट सिर्जना गर्न मोडेलिङ निर्देशनहरूको संक्षिप्त सेट प्रयोग गरें। लगातार आउटपुट प्राप्त गर्न मैले केही पटक प्रम्प्ट इन्जिनियर गर्नुपर्‍यो।


शून्य-शट उदाहरणले अपेक्षाकृत राम्रो काम गर्यो, तर मैले फेला पारे कि आउटपुट असंगत थियो। JSON आउटपुट होल्ड गर्नको लागि संरचित आउटपुट परिभाषित गर्दा वास्तवमै मद्दत भयो:


 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")

केही-शट उदाहरण आउटपुट

JSON आफै पनि असंगत थियो, त्यसैले मैले चलचित्र सिफारिस डेटासेटमा आधारित स्कीमा परिभाषित गरें।


उदाहरण आउटपुट:


 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"]), ], ), ]


मैले कडा JSON स्कीमाबाट विचलित हुनुपर्‍यो र LLM लाई आयात लिपि उत्पन्न गर्न मद्दतको लागि आउटपुटमा column_name फिल्ड थप्नुपर्‍यो। वर्णनका उदाहरणहरू प्रदान गर्दा पनि यस सन्दर्भमा मद्दत भयो, अन्यथा MATCH खण्डमा प्रयोग गरिएका गुणहरू असंगत थिए।

चेन

यहाँ अन्तिम प्रम्प्ट छ:


 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)


चेन कार्यान्वयन गर्दै

मोडेललाई पुनरावृत्ति रूपमा अद्यावधिक गर्न, मैले डाटाफ्रेममा कुञ्जीहरू दोहोर्याएँ र प्रत्येक कुञ्जी, यसको डाटाटाइप, र पहिलो पाँच अद्वितीय मानहरूलाई प्रम्प्टमा पास गरें:


 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


कन्सोल आउटपुट:


 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']


प्रयोगका केसहरू ह्यान्डल गर्न प्रम्प्टमा केही ट्वीकहरू पछि, मैले एउटा मोडेलको साथ समाप्त गरें जसमा म धेरै खुसी थिएँ। LLM ले डेटासेटमा ट्र्याक, कलाकार, र PERFORMED_BY सम्बन्ध दुईलाई जोड्न समावेश गरेको निर्धारण गर्न व्यवस्थित गरेको थियो:


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

अद्वितीय पहिचानकर्ताहरू थप्दै

मैले याद गरें कि स्कीमाले कुनै पनि अद्वितीय पहिचानकर्ताहरू समावेश गर्दैन, र यो सम्बन्ध आयात गर्दा समस्या हुन सक्छ। फरक– फरक कलाकारले एउटै नामका गीत रिलिज गर्ने र दुईजना कलाकारको एउटै नाम हुनसक्ने तर्क छ ।


यस कारणका लागि, ट्र्याकहरूको लागि पहिचानकर्ता सिर्जना गर्न महत्त्वपूर्ण थियो ताकि तिनीहरू ठूलो डेटासेट भित्र फरक गर्न सकिन्छ:


 # 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)


यो चरण साँच्चै नोडहरूको लागि मात्र आवश्यक छ, त्यसैले मैले स्किमाबाट नोडहरू निकालें, प्रत्येकको लागि चेन चलाएँ र त्यसपछि अद्यावधिक गरिएका परिभाषाहरूसँग सम्बन्धहरू जोडे:


 # 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

डाटा मोडेल समीक्षा

विवेकको लागि, यो अनुकूलनको लागि मोडेल जाँच गर्न लायक छ। model_prompt ले संज्ञा र क्रियाहरू पहिचान गर्न राम्रो काम गर्यो, तर अझ जटिल मोडेलमा।


एउटा पुनरावृत्तिले *_प्लेलिस्ट र _चार्ट स्तम्भहरूलाई आईडीको रूपमा व्यवहार गर्यो र स्ट्रिम नोडहरू र IN_PLAYLIST सम्बन्धहरू सिर्जना गर्ने प्रयास गर्यो। मैले यो अल्पविराम (जस्तै, 1,001) संग ढाँचा सहित 1,000 भन्दा बढी गणनाको कारणले भएको अनुमान गर्छु।


राम्रो विचार, तर शायद अलि धेरै चलाख। तर यसले डेटा संरचना बुझ्ने लूपमा मानव हुनुको महत्त्व देखाउँछ।


 # 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


वास्तविक-विश्व परिदृश्यमा, म यसलाई डेटा मोडेललाई पुनरावृत्ति सुधार गर्न केही पटक चलाउन चाहन्छु। म एक अधिकतम सीमा राख्छु, त्यसपछि त्यो बिन्दु सम्म दोहोर्याउनुहोस् वा डेटा मोडेल वस्तु अब परिवर्तन हुनेछैन।

आयात विवरणहरू उत्पन्न गर्नुहोस्

यस बिन्दुमा, स्किमा पर्याप्त बलियो हुनुपर्छ र LLM लाई आयात लिपिहरूको सेट उत्पन्न गर्न अनुमति दिन सकेसम्म धेरै जानकारी समावेश गर्नुपर्छ।


Neo4j डाटा आयात सिफारिसहरू अनुरूप, फाइल धेरै पटक प्रशोधन गरिनु पर्छ, प्रत्येक पटक उत्सुक अपरेशनहरू र लक गर्नबाट बच्न एकल नोड वा सम्बन्ध आयात गर्न।


 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} """)


यस चेनलाई अघिल्लो चरणहरूमा फरक आउटपुट वस्तु चाहिन्छ। यस अवस्थामा, साइफर सदस्य सबैभन्दा महत्त्वपूर्ण छ, तर मैले चेन अफ थॉटलाई प्रोत्साहित गर्न chain_of_thought कुञ्जी पनि समावेश गर्न चाहन्थे:


 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)


उही प्रक्रिया त्यसपछि समीक्षा गरिएका प्रत्येक परिभाषाहरूमा दोहोर्याउन र साइफर उत्पन्न गर्न लागू हुन्छ:


 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)


कन्सोल आउटपुट:


 ------ 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)


यो प्रम्प्टले लगातार परिणामहरू प्राप्त गर्न केही ईन्जिनियरिङ् लियो:


  • कहिलेकाहीँ साइफरले मर्ज कथनलाई धेरै क्षेत्रहरू परिभाषित गरी समावेश गर्दछ, जुन सबभन्दा राम्रो हुन्छ। यदि कुनै पनि स्तम्भहरू शून्य छन् भने, सम्पूर्ण आयात असफल हुनेछ।
  • कहिलेकाहीँ, परिणामले apoc.period.iterate समावेश गर्दछ, जुन अब आवश्यक छैन, र म पाइथन ड्राइभरसँग कार्यान्वयन गर्न सक्ने कोड चाहन्थें।
  • सम्बन्धहरू सिर्जना गर्दा निर्दिष्ट स्तम्भको नाम प्रयोग गर्नुपर्छ भनेर मैले दोहोर्याउनु परेको थियो।
  • सम्बन्धको प्रत्येक छेउमा नोडहरूमा अद्वितीय पहिचानकर्ता प्रयोग गर्दा LLM ले निर्देशनहरू पालना गर्दैन, त्यसैले यसले वर्णनमा निर्देशनहरू पालना गर्न केही प्रयासहरू गर्यो। यस प्रम्प्ट र model_prompt बीच केही अगाडि र पछाडि थियो।
  • ब्याकटिकहरू स्तम्भ नामहरूको लागि आवश्यक थियो जसमा विशेष क्यारेक्टरहरू समावेश थिए (उदाहरण ऊर्जा_%)।


यसलाई दुई प्रम्प्टहरूमा विभाजन गर्न पनि फाइदाजनक हुनेछ - एउटा नोडहरूको लागि र अर्को सम्बन्धहरूको लागि। तर त्यो अर्को दिनको लागि काम हो।

अद्वितीय अवरोधहरू सिर्जना गर्नुहोस्

अर्को, डाटाबेसमा अद्वितीय अवरोधहरू सिर्जना गर्न आयात लिपिहरू आधारको रूपमा प्रयोग गर्न सकिन्छ:


 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)


कन्सोल आउटपुट:


 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


कहिलेकाहीँ यो प्रम्प्टले अनुक्रमणिका र अवरोधहरूका लागि कथनहरू फर्काउँछ, सेमी-कोलनमा विभाजन गर्दछ।

आयात चलाउनुहोस्

सबै कुराको साथमा, यो ethe साइफर कथनहरू कार्यान्वयन गर्ने समय थियो:


 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)

डाटासेटमा QA

GraphCypherQAChain प्रयोग गरेर डाटासेटमा केही QA बिना यो पोस्ट पूरा हुने छैन:


 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 )

सबैभन्दा लोकप्रिय कलाकारहरू

डाटाबेसमा सबैभन्दा लोकप्रिय कलाकारहरू को हुन्?


 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 ले लोकप्रियतालाई एक कलाकारले स्ट्रिमहरूको समग्र संख्याको सट्टामा ट्र्याकहरूको संख्याको आधारमा न्याय गरेको देखिन्छ।

बिट्स प्रति मिनेट

कुन ट्र्याकमा उच्च BPM छ?


 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." }

साइफर जेनेरेशन प्रम्प्ट सुधार गर्दै

यस अवस्थामा, साइफर राम्रो देखिन्छ र सही परिणाम प्रम्प्टमा समावेश गरिएको थियो तर gpt-4o ले जवाफ व्याख्या गर्न सकेन। GraphCypherQAChain लाई पास गरिएको CYPHER_GENERATION_PROMPT ले स्तम्भका नामहरूलाई थप भ्रामक बनाउनको लागि थप निर्देशनहरू गर्न सक्छ जस्तो देखिन्छ।


लेबल र गुण नामहरू प्रयोग गरेर साइफर कथनमा सधैं वर्बोज स्तम्भ नामहरू प्रयोग गर्नुहोस्। उदाहरणका लागि, 'name' को सट्टा 'person_name' प्रयोग गर्नुहोस्।


GraphCypherQAChain कस्टम प्रम्प्टको साथ:


 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, )

अधिकांश कलाकारहरूद्वारा प्रदर्शन गरिएका ट्र्याकहरू

प्रकार र दिशा अनुसार सम्बन्धहरूको संख्याको गणना फर्काउन ग्राफहरू उत्कृष्ट हुन्छन्।


 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." }

सारांश

CSV विश्लेषण र मोडलिङ सबैभन्दा समय-गहन भाग हो। यसलाई उत्पन्न गर्न पाँच मिनेट भन्दा बढी लाग्न सक्छ।


लागत आफैं धेरै सस्तो थियो। आठ घण्टाको प्रयोगमा, मैले सयौं अनुरोधहरू पठाएको हुनुपर्छ र मैले एक डलर वा सो खर्च गरें।


यस बिन्दुमा पुग्न धेरै चुनौतीहरू थिए:


  • प्रम्प्टहरूले सही प्राप्त गर्न धेरै पुनरावृत्तिहरू लिए। यो समस्या मोडेललाई फाइन-ट्युनिङ गरेर वा केही शट उदाहरणहरू प्रदान गरेर हटाउन सकिन्छ।
  • GPT-4o बाट JSON प्रतिक्रियाहरू असंगत हुन सक्छन्। मलाई json-repair सिफारिस गरिएको थियो, जुन LLM लाई यसको आफ्नै JSON आउटपुट प्रमाणित गर्न प्रयास गर्नु भन्दा राम्रो थियो।


मैले यो दृष्टिकोणलाई LangGraph कार्यान्वयनमा राम्रोसँग काम गरिरहेको देख्न सक्छु जहाँ अपरेशनहरू अनुक्रममा चलाइन्छ, LLM लाई मोडेल निर्माण र परिष्कृत गर्ने क्षमता दिँदै। नयाँ मोडलहरू रिलिज हुने बित्तिकै, तिनीहरू फाइन-ट्युनिङबाट पनि फाइदा लिन सक्छन्।

थप जान्नुहोस्

LLM सँग ज्ञान ग्राफ निर्माण प्रक्रियालाई सुव्यवस्थित गर्ने बारे थप जानकारीको लागि Neo4j सँग ठूला भाषा मोडेलहरू प्रयोग गर्ने जाँच गर्नुहोस्। LangGraph र Neo4j बारे थप जानकारीको लागि LangChain र LangGraph प्रयोग गरेर Neo4j GraphRAG कार्यप्रवाह सिर्जना गर्नुहोस् पढ्नुहोस्। र फाइन-ट्यूनिङको बारेमा थप जान्नको लागि, ज्ञान ग्राफहरू र LLMs: Fine-Tuning vs. Retrieval-Augmented Generation हेर्नुहोस्।


सुविधा छवि: ग्राफ मोडेलले कलाकारहरूसँग PERFORMED_BY सम्बन्धहरू भएका ट्र्याकहरू देखाउँछ। लेखक द्वारा फोटो।


यस विषयमा थप जान्नको लागि, नोभेम्बर 7 मा NODES 2024 मा हामीसँग सामेल हुनुहोस्, हाम्रो नि:शुल्क भर्चुअल विकासकर्ता सम्मेलन बौद्धिक एपहरू, ज्ञान ग्राफहरू, र AI मा। अहिले दर्ता गर्नुहोस्!