Dataset Viewer
conversations
stringlengths 5.43k
5.96k
|
|---|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with high dividend yield"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high dividend yield\":[\"preference/high\",\"attribute/fundamental/yield/dividend\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me dividend yield mutual funds"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"dividend yield\":[\"preference/high\",\"attribute/fundamental/yield/dividend\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"dividend yield mutual funds\":[\"sebi_classification/equity_schemes/dividend_yield_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high alpha and low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with high returns and low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high returns\":[\"preference/high\",\"attribute/technical/returns/annualized_returns\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "recommend equity funds with low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"equity\":[\"asset_type/equity\"]},{\"funds\":[\"vehicle/funds\"]},{\"equity funds\":[\"sebi_classification/equity_schemes\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with high alpha and low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high risk-adjusted returns"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high risk-adjusted returns\":[\"preference/high\",\"attribute/technical/returns/risk_adjusted_returns\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "small cap funds with high volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"small cap\":[\"preference/high\",\"attribute/style/size/small_cap\"]},{\"funds\":[\"vehicle/funds\"]},{\"small cap funds\":[\"sebi_classification/equity_schemes/small_cap_fund\"]},{\"high volatility\":[\"preference/high\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me mutual funds focused on telecom services"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"telecom services\":[\"preference/high\",\"exposure/sector/communication_services/telecommunication_services\"]},{\"mutual funds focused on telecom services\":[\"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "low volatility funds"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]},{\"funds\":[\"vehicle/funds\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high annualized returns from last year"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high annualized returns from last year\":[\"preference/high\",\"time/1Y\",\"attribute/technical/returns/annualized_returns\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with high alpha returns focusing on IT sector"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]},{\"IT sector\":[\"preference/high\",\"exposure/sector/information_technology\"]},{\"funds focusing on IT sector\":[\"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "list funds with high dividend yields"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high dividend yields\":[\"preference/high\",\"attribute/fundamental/yield/dividend\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "looking for large cap funds with annualized returns over 15%"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"large cap\":[\"preference/high\",\"attribute/style/size/large_cap\"]},{\"funds\":[\"vehicle/funds\"]},{\"large cap funds\":[\"sebi_classification/equity_schemes/large_cap_fund\"]},{\"annualized returns\":[\"preference/>15%\",\"attribute/technical/returns/annualized_returns\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "recommend funds with low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high dividend yield and low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high dividend yield\":[\"preference/high\",\"attribute/fundamental/yield/dividend\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with high alpha"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds with low beta over the last year"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"low beta\":[\"preference/low\",\"time/1Y\",\"attribute/technical/beta\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "best small cap funds with low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"small cap\":[\"preference/high\",\"attribute/style/size/small_cap\"]},{\"funds\":[\"vehicle/funds\"]},{\"small cap funds\":[\"sebi_classification/equity_schemes/small_cap_fund\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "worst small cap funds with low volatility"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"worst\":[\"preference/low\",\"attribute/technical/performance\"]},{\"small cap\":[\"preference/high\",\"attribute/style/size/small_cap\"]},{\"funds\":[\"vehicle/funds\"]},{\"small cap funds\":[\"sebi_classification/equity_schemes/small_cap_fund\"]},{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high momentum exposure"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high momentum exposure\":[\"preference/high\",\"exposure/factor/momentum\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "show me funds in the tech sector"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"tech sector\":[\"preference/high\",\"exposure/sector/information_technology\"]},{\"funds in the tech sector\":[\"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "find funds with high alpha"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "low volatility funds with high momentum"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"low volatility\":[\"preference/low\",\"attribute/technical/risk/volatility\"]},{\"funds\":[\"vehicle/funds\"]},{\"high momentum\":[\"preference/high\",\"exposure/factor/momentum\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "best alpha funds"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]},{\"funds\":[\"vehicle/funds\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with good credit rating"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"good credit rating\":[\"preference/high\",\"attribute/fundamental/credit_rating\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high alpha"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high alpha\":[\"preference/high\",\"attribute/technical/returns/alpha\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high beta and small cap focus"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high beta\":[\"preference/high\",\"attribute/technical/beta\"]},{\"small cap focus\":[\"preference/high\",\"attribute/style/size/small_cap\"]},{\"small cap focus\":[\"sebi_classification/equity_schemes/small_cap_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high dividend yield"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high dividend yield\":[\"preference/high\",\"attribute/fundamental/yield/dividend\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "funds with high credit rating"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"high credit rating\":[\"preference/high\",\"attribute/fundamental/credit_rating\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "find funds with strong momentum"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"strong momentum\":[\"preference/high\",\"exposure/factor/momentum\"]}]}"}]
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 10