From a0a007115d393d9c0029f1174f09e04a015c9ff8 Mon Sep 17 00:00:00 2001 From: Alonso Guevara Date: Thu, 1 Aug 2024 17:27:08 -0600 Subject: [PATCH] Update prompt tune prompts (#794) * Update prompts in prompt tune * Update prompt tuning meta prompts * Semver * Formatting * Update examples --- .../minor-20240801001005275591.json | 4 + .../prompt_tune/prompt/entity_relationship.py | 155 ++++++++++++++++-- .../prompt_tune/template/entity_extraction.py | 6 +- 3 files changed, 148 insertions(+), 17 deletions(-) create mode 100644 .semversioner/next-release/minor-20240801001005275591.json diff --git a/.semversioner/next-release/minor-20240801001005275591.json b/.semversioner/next-release/minor-20240801001005275591.json new file mode 100644 index 000000000..819bd782a --- /dev/null +++ b/.semversioner/next-release/minor-20240801001005275591.json @@ -0,0 +1,4 @@ +{ + "type": "minor", + "description": "Update Prompt Tuning meta prompts with finer examples" +} diff --git a/graphrag/prompt_tune/prompt/entity_relationship.py b/graphrag/prompt_tune/prompt/entity_relationship.py index b2c20eb29..4024a9131 100644 --- a/graphrag/prompt_tune/prompt/entity_relationship.py +++ b/graphrag/prompt_tune/prompt/entity_relationship.py @@ -12,8 +12,7 @@ - entity_name: Name of the entity, capitalized - entity_type: One of the following types: [{entity_types}] - entity_description: Comprehensive description of the entity's attributes and activities -Format each entity, include the parenthesis at the beginning and end, as ("entity"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} -for example: ("entity"{{tuple_delimiter}}"Microsoft"{{tuple_delimiter}}"organization"{{tuple_delimiter}}"Microsoft is a technology company"){{record_delimiter}} +Format each entity as ("entity"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} 2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other. For each pair of related entities, extract the following information: @@ -21,8 +20,7 @@ - target_entity: name of the target entity, as identified in step 1 - relationship_description: explanation as to why you think the source entity and the target entity are related to each other - relationship_strength: an integer score between 1 to 10, indicating strength of the relationship between the source entity and target entity -Format each relationship, include the parenthesis at the beginning and end, as ("relationship"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} -for example: ("relationship"{{tuple_delimiter}}"company A"{{tuple_delimiter}}"person A"{{tuple_delimiter}}"company A is currently owned by person A"{{tuple_delimiter}}8){{record_delimiter}} +Format each relationship as ("relationship"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} 3. Use **{{record_delimiter}}** as the list delimiter. @@ -30,6 +28,41 @@ 5. When finished, output {{completion_delimiter}}. +###################### +-Examples- +###################### +Example 1: +Entity_types: ORGANIZATION,PERSON +Text: +The Verdantis's Central Institution is scheduled to meet on Monday and Thursday, with the institution planning to release its latest policy decision on Thursday at 1:30 p.m. PDT, followed by a press conference where Central Institution Chair Martin Smith will take questions. Investors expect the Market Strategy Committee to hold its benchmark interest rate steady in a range of 3.5%-3.75%. +###################### +Output: +("entity"{{tuple_delimiter}}CENTRAL INSTITUTION{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Central Institution is the Federal Reserve of Verdantis, which is setting interest rates on Monday and Thursday) +{{record_delimiter}} +("entity"{{tuple_delimiter}}MARTIN SMITH{{tuple_delimiter}}PERSON{{tuple_delimiter}}Martin Smith is the chair of the Central Institution) +{{record_delimiter}} +("entity"{{tuple_delimiter}}MARKET STRATEGY COMMITTEE{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Central Institution committee makes key decisions about interest rates and the growth of Verdantis's money supply) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}MARTIN SMITH{{tuple_delimiter}}CENTRAL INSTITUTION{{tuple_delimiter}}Martin Smith is the Chair of the Central Institution and will answer questions at a press conference{{tuple_delimiter}}9) +{{completion_delimiter}} + +###################### +Example 2: +Entity_types: ORGANIZATION +Text: +TechGlobal's (TG) stock skyrocketed in its opening day on the Global Exchange Thursday. But IPO experts warn that the semiconductor corporation's debut on the public markets isn't indicative of how other newly listed companies may perform. + +TechGlobal, a formerly public company, was taken private by Vision Holdings in 2014. The well-established chip designer says it powers 85% of premium smartphones. +###################### +Output: +("entity"{{tuple_delimiter}}TECHGLOBAL{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}TechGlobal is a stock now listed on the Global Exchange which powers 85% of premium smartphones) +{{record_delimiter}} +("entity"{{tuple_delimiter}}VISION HOLDINGS{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}Vision Holdings is a firm that previously owned TechGlobal) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}TECHGLOBAL{{tuple_delimiter}}VISION HOLDINGS{{tuple_delimiter}}Vision Holdings formerly owned TechGlobal from 2014 until present{{tuple_delimiter}}5) +{{completion_delimiter}} + + -Real Data- ###################### entity_types: {entity_types} @@ -63,7 +96,39 @@ {{"source": , "target": , "relationship": , "relationship_strength": }} -3. Return output in {language} as a single list of all JSON entities and relationships identified in steps 1 and 2. If you have to translate, just translate the descriptions, nothing else! +3. Return output in {language} as a single list of all JSON entities and relationships identified in steps 1 and 2. + +4. If you have to translate into {language}, just translate the descriptions, nothing else! + +###################### +-Examples- +###################### +Example 1: +Text: +The Verdantis's Central Institution is scheduled to meet on Monday and Thursday, with the institution planning to release its latest policy decision on Thursday at 1:30 p.m. PDT, followed by a press conference where Central Institution Chair Martin Smith will take questions. Investors expect the Market Strategy Committee to hold its benchmark interest rate steady in a range of 3.5%-3.75%. +###################### +Output: +[ + {{"name": "CENTRAL INSTITUTION", "type": "ORGANIZATION", "description": "The Central Institution is the Federal Reserve of Verdantis, which is setting interest rates on Monday and Thursday"}}, + {{"name": "MARTIN SMITH", "type": "PERSON", "description": "Martin Smith is the chair of the Central Institution"}}, + {{"name": "MARKET STRATEGY COMMITTEE", "type": "ORGANIZATION", "description": "The Central Institution committee makes key decisions about interest rates and the growth of Verdantis's money supply"}}, + {{"source": "MARTIN SMITH", "target": "CENTRAL INSTITUTION", "relationship": "Martin Smith is the Chair of the Central Institution and will answer questions at a press conference", "relationship_strength": 9}} +] + +###################### +Example 2: +Text: +TechGlobal's (TG) stock skyrocketed in its opening day on the Global Exchange Thursday. But IPO experts warn that the semiconductor corporation's debut on the public markets isn't indicative of how other newly listed companies may perform. + +TechGlobal, a formerly public company, was taken private by Vision Holdings in 2014. The well-established chip designer says it powers 85% of premium smartphones. +###################### +Output: +[ + {{"name": "TECHGLOBAL", "type": "ORGANIZATION", "description": "TechGlobal is a stock now listed on the Global Exchange which powers 85% of premium smartphones"}}, + {{"name": "VISION HOLDINGS", "type": "ORGANIZATION", "description": "Vision Holdings is a firm that previously owned TechGlobal"}}, + {{"source": "TECHGLOBAL", "target": "VISION HOLDINGS", "relationship": "Vision Holdings formerly owned TechGlobal from 2014 until present", "relationship_strength": 5}} +] + -Real Data- ###################### @@ -102,31 +167,91 @@ ###################### -Examples- ###################### +Example 1: Text: -The Fed is scheduled to meet on Tuesday and Wednesday, with the central bank planning to release its latest policy decision on Wednesday at 2:00 p.m. ET, followed by a press conference where Fed Chair Jerome Powell will take questions. Investors expect the Federal Open Market Committee to hold its benchmark interest rate steady in a range of 5.25%-5.5%. +The Verdantis's Central Institution is scheduled to meet on Monday and Thursday, with the institution planning to release its latest policy decision on Thursday at 1:30 p.m. PDT, followed by a press conference where Central Institution Chair Martin Smith will take questions. Investors expect the Market Strategy Committee to hold its benchmark interest rate steady in a range of 3.5%-3.75%. ###################### Output: -("entity"{{tuple_delimiter}}FED{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Fed is the Federal Reserve, which is setting interest rates on Tuesday and Wednesday) +("entity"{{tuple_delimiter}}CENTRAL INSTITUTION{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Central Institution is the Federal Reserve of Verdantis, which is setting interest rates on Monday and Thursday) {{record_delimiter}} -("entity"{{tuple_delimiter}}JEROME POWELL{{tuple_delimiter}}PERSON{{tuple_delimiter}}Jerome Powell is the chair of the Federal Reserve) +("entity"{{tuple_delimiter}}MARTIN SMITH{{tuple_delimiter}}PERSON{{tuple_delimiter}}Martin Smith is the chair of the Central Institution) {{record_delimiter}} -("entity"{{tuple_delimiter}}FEDERAL OPEN MARKET COMMITTEE{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Federal Reserve committee makes key decisions about interest rates and the growth of the United States money supply) +("entity"{{tuple_delimiter}}MARKET STRATEGY COMMITTEE{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}The Central Institution committee makes key decisions about interest rates and the growth of Verdantis's money supply) {{record_delimiter}} -("relationship"{{tuple_delimiter}}JEROME POWELL{{tuple_delimiter}}FED{{tuple_delimiter}}Jerome Powell is the Chair of the Federal Reserve and will answer questions at a press conference{{tuple_delimiter}}9) +("relationship"{{tuple_delimiter}}MARTIN SMITH{{tuple_delimiter}}CENTRAL INSTITUTION{{tuple_delimiter}}Martin Smith is the Chair of the Central Institution and will answer questions at a press conference{{tuple_delimiter}}9) {{completion_delimiter}} + ###################### +Example 2: Text: -Arm's (ARM) stock skyrocketed in its opening day on the Nasdaq Thursday. But IPO experts warn that the British chipmaker's debut on the public markets isn't indicative of how other newly listed companies may perform. +TechGlobal's (TG) stock skyrocketed in its opening day on the Global Exchange Thursday. But IPO experts warn that the semiconductor corporation's debut on the public markets isn't indicative of how other newly listed companies may perform. -Arm, a formerly public company, was taken private by SoftBank in 2016. The well-established chip designer says it powers 99% of premium smartphones. +TechGlobal, a formerly public company, was taken private by Vision Holdings in 2014. The well-established chip designer says it powers 85% of premium smartphones. ###################### Output: -("entity"{{tuple_delimiter}}ARM{{tuple_delimiter}}ORGANIZATION, COMPANY{{tuple_delimiter}}Arm is a stock now listed on the Nasdaq which powers 99% of premium smartphones) +("entity"{{tuple_delimiter}}TECHGLOBAL{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}TechGlobal is a stock now listed on the Global Exchange which powers 85% of premium smartphones) +{{record_delimiter}} +("entity"{{tuple_delimiter}}VISION HOLDINGS{{tuple_delimiter}}ORGANIZATION{{tuple_delimiter}}Vision Holdings is a firm that previously owned TechGlobal) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}TECHGLOBAL{{tuple_delimiter}}VISION HOLDINGS{{tuple_delimiter}}Vision Holdings formerly owned TechGlobal from 2014 until present{{tuple_delimiter}}5) +{{completion_delimiter}} + +###################### +Example 3: +Text: +Five Aurelians jailed for 8 years in Firuzabad and widely regarded as hostages are on their way home to Aurelia. + +The swap orchestrated by Quintara was finalized when $8bn of Firuzi funds were transferred to financial institutions in Krohaara, the capital of Quintara. + +The exchange initiated in Firuzabad's capital, Tiruzia, led to the four men and one woman, who are also Firuzi nationals, boarding a chartered flight to Krohaara. + +They were welcomed by senior Aurelian officials and are now on their way to Aurelia's capital, Cashion. + +The Aurelians include 39-year-old businessman Samuel Namara, who has been held in Tiruzia's Alhamia Prison, as well as journalist Durke Bataglani, 59, and environmentalist Meggie Tazbah, 53, who also holds Bratinas nationality. +###################### +Output: +("entity"{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}GEO{{tuple_delimiter}}Firuzabad held Aurelians as hostages) +{{record_delimiter}} +("entity"{{tuple_delimiter}}AURELIA{{tuple_delimiter}}GEO{{tuple_delimiter}}Country seeking to release hostages) +{{record_delimiter}} +("entity"{{tuple_delimiter}}QUINTARA{{tuple_delimiter}}GEO{{tuple_delimiter}}Country that negotiated a swap of money in exchange for hostages) {{record_delimiter}} -("entity"{{tuple_delimiter}}SOFTBANK{{tuple_delimiter}}ORGANIZATION, COMPANY{{tuple_delimiter}}SoftBank is a firm that previously owned Arm) {{record_delimiter}} -("relationship"{{tuple_delimiter}}ARM{{tuple_delimiter}}SOFTBANK{{tuple_delimiter}}SoftBank formerly owned Arm from 2016 until present{{tuple_delimiter}}5) +("entity"{{tuple_delimiter}}TIRUZIA{{tuple_delimiter}}GEO{{tuple_delimiter}}Capital of Firuzabad where the Aurelians were being held) +{{record_delimiter}} +("entity"{{tuple_delimiter}}KROHAARA{{tuple_delimiter}}GEO{{tuple_delimiter}}Capital city in Quintara) +{{record_delimiter}} +("entity"{{tuple_delimiter}}CASHION{{tuple_delimiter}}GEO{{tuple_delimiter}}Capital city in Aurelia) +{{record_delimiter}} +("entity"{{tuple_delimiter}}SAMUEL NAMARA{{tuple_delimiter}}PERSON{{tuple_delimiter}}Aurelian who spent time in Tiruzia's Alhamia Prison) +{{record_delimiter}} +("entity"{{tuple_delimiter}}ALHAMIA PRISON{{tuple_delimiter}}GEO{{tuple_delimiter}}Prison in Tiruzia) +{{record_delimiter}} +("entity"{{tuple_delimiter}}DURKE BATAGLANI{{tuple_delimiter}}PERSON{{tuple_delimiter}}Aurelian journalist who was held hostage) +{{record_delimiter}} +("entity"{{tuple_delimiter}}MEGGIE TAZBAH{{tuple_delimiter}}PERSON{{tuple_delimiter}}Bratinas national and environmentalist who was held hostage) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}AURELIA{{tuple_delimiter}}Firuzabad negotiated a hostage exchange with Aurelia{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}QUINTARA{{tuple_delimiter}}AURELIA{{tuple_delimiter}}Quintara brokered the hostage exchange between Firuzabad and Aurelia{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}QUINTARA{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}Quintara brokered the hostage exchange between Firuzabad and Aurelia{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}SAMUEL NAMARA{{tuple_delimiter}}ALHAMIA PRISON{{tuple_delimiter}}Samuel Namara was a prisoner at Alhamia prison{{tuple_delimiter}}8) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}SAMUEL NAMARA{{tuple_delimiter}}MEGGIE TAZBAH{{tuple_delimiter}}Samuel Namara and Meggie Tazbah were exchanged in the same hostage release{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}SAMUEL NAMARA{{tuple_delimiter}}DURKE BATAGLANI{{tuple_delimiter}}Samuel Namara and Durke Bataglani were exchanged in the same hostage release{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}MEGGIE TAZBAH{{tuple_delimiter}}DURKE BATAGLANI{{tuple_delimiter}}Meggie Tazbah and Durke Bataglani were exchanged in the same hostage release{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}SAMUEL NAMARA{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}Samuel Namara was a hostage in Firuzabad{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}MEGGIE TAZBAH{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}Meggie Tazbah was a hostage in Firuzabad{{tuple_delimiter}}2) +{{record_delimiter}} +("relationship"{{tuple_delimiter}}DURKE BATAGLANI{{tuple_delimiter}}FIRUZABAD{{tuple_delimiter}}Durke Bataglani was a hostage in Firuzabad{{tuple_delimiter}}2) {{completion_delimiter}} + ###################### -Real Data- ###################### diff --git a/graphrag/prompt_tune/template/entity_extraction.py b/graphrag/prompt_tune/template/entity_extraction.py index 9ff10a23f..d2e1c60b0 100644 --- a/graphrag/prompt_tune/template/entity_extraction.py +++ b/graphrag/prompt_tune/template/entity_extraction.py @@ -63,7 +63,9 @@ {{"source": , "target": , "relationship": , "relationship_strength": }} -3. Return output in {language} as a single list of all JSON entities and relationships identified in steps 1 and 2. If you have to translate, just translate the descriptions, nothing else! +3. Return output in {language} as a single list of all JSON entities and relationships identified in steps 1 and 2. + +4. If you have to translate into {language}, just translate the descriptions, nothing else! -Examples- ###################### @@ -120,7 +122,7 @@ - target_entity: name of the target entity, as identified in step 1 - relationship_description: explanation as to why you think the source entity and the target entity are related to each other - relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity - Format each relationship as ("relationship"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} +Format each relationship as ("relationship"{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}{{tuple_delimiter}}){{record_delimiter}} 3. Use **{{record_delimiter}}** as the list delimiter.