From 0cfffda1ff1264ab37869b91fe7233871c64a13a Mon Sep 17 00:00:00 2001 From: Erick Friis Date: Mon, 18 Dec 2023 11:26:57 -0800 Subject: [PATCH] custom --- docs/docs/guides/model_laboratory.ipynb | 6 +++--- .../docs/integrations/callbacks/argilla.ipynb | 2 +- .../integrations/callbacks/confident.ipynb | 2 +- docs/docs/integrations/callbacks/infino.ipynb | 20 +++++++++---------- docs/docs/integrations/llms/openlm.ipynb | 6 +++--- .../integrations/llms/predictionguard.ipynb | 6 +++--- .../providers/clearml_tracking.ipynb | 18 ++++++++--------- .../providers/javelin_ai_gateway.mdx | 2 +- docs/docs/integrations/providers/mlflow.mdx | 2 +- .../providers/mlflow_ai_gateway.mdx | 2 +- .../providers/whylabs_profiling.ipynb | 4 ++-- docs/docs/integrations/toolkits/openapi.ipynb | 10 +++++----- .../integrations/toolkits/openapi_nla.ipynb | 2 +- .../chains/foundational/llm_chain.ipynb | 2 +- docs/docs/modules/model_io/llms/index.ipynb | 2 +- .../llms/test_predictionguard.py | 2 +- 16 files changed, 44 insertions(+), 44 deletions(-) diff --git a/docs/docs/guides/model_laboratory.ipynb b/docs/docs/guides/model_laboratory.ipynb index 893f3f0557e4d..c3c650feaa5a6 100644 --- a/docs/docs/guides/model_laboratory.ipynb +++ b/docs/docs/guides/model_laboratory.ipynb @@ -62,7 +62,7 @@ "What color is a flamingo?\n", "\n", "\u001b[1mOpenAI\u001b[0m\n", - "Params: {'model': 'gpt-3.5-turbo-instruct', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", + "Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", "\u001b[36;1m\u001b[1;3m\n", "\n", "Flamingos are pink.\u001b[0m\n", @@ -111,7 +111,7 @@ "New York\n", "\n", "\u001b[1mOpenAI\u001b[0m\n", - "Params: {'model': 'gpt-3.5-turbo-instruct', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", + "Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", "\u001b[36;1m\u001b[1;3m\n", "\n", "The capital of New York is Albany.\u001b[0m\n", @@ -191,7 +191,7 @@ "What is the hometown of the reigning men's U.S. Open champion?\n", "\n", "\u001b[1mOpenAI\u001b[0m\n", - "Params: {'model': 'gpt-3.5-turbo-instruct', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", + "Params: {'model': 'text-davinci-002', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1}\n", "\n", "\n", "\u001b[1m> Entering new chain...\u001b[0m\n", diff --git a/docs/docs/integrations/callbacks/argilla.ipynb b/docs/docs/integrations/callbacks/argilla.ipynb index 40c1ae15c944b..9e89cb5da9249 100644 --- a/docs/docs/integrations/callbacks/argilla.ipynb +++ b/docs/docs/integrations/callbacks/argilla.ipynb @@ -205,7 +205,7 @@ { "data": { "text/plain": [ - "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when he hit the wall? \\nA: Dam.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nThe Moon \\n\\nThe moon is high in the midnight sky,\\nSparkling like a star above.\\nThe night so peaceful, so serene,\\nFilling up the air with love.\\n\\nEver changing and renewing,\\nA never-ending light of grace.\\nThe moon remains a constant view,\\nA reminder of life’s gentle pace.\\n\\nThrough time and space it guides us on,\\nA never-fading beacon of hope.\\nThe moon shines down on us all,\\nAs it continues to rise and elope.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ. What did one magnet say to the other magnet?\\nA. \"I find you very attractive!\"', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nThe world is charged with the grandeur of God.\\nIt will flame out, like shining from shook foil;\\nIt gathers to a greatness, like the ooze of oil\\nCrushed. Why do men then now not reck his rod?\\n\\nGenerations have trod, have trod, have trod;\\nAnd all is seared with trade; bleared, smeared with toil;\\nAnd wears man's smudge and shares man's smell: the soil\\nIs bare now, nor can foot feel, being shod.\\n\\nAnd for all this, nature is never spent;\\nThere lives the dearest freshness deep down things;\\nAnd though the last lights off the black West went\\nOh, morning, at the brown brink eastward, springs —\\n\\nBecause the Holy Ghost over the bent\\nWorld broods with warm breast and with ah! bright wings.\\n\\n~Gerard Manley Hopkins\", generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ: What did one ocean say to the other ocean?\\nA: Nothing, they just waved.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nA poem for you\\n\\nOn a field of green\\n\\nThe sky so blue\\n\\nA gentle breeze, the sun above\\n\\nA beautiful world, for us to love\\n\\nLife is a journey, full of surprise\\n\\nFull of joy and full of surprise\\n\\nBe brave and take small steps\\n\\nThe future will be revealed with depth\\n\\nIn the morning, when dawn arrives\\n\\nA fresh start, no reason to hide\\n\\nSomewhere down the road, there's a heart that beats\\n\\nBelieve in yourself, you'll always succeed.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 504, 'total_tokens': 528, 'prompt_tokens': 24}, 'model_name': 'gpt-3.5-turbo-instruct'})" + "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when he hit the wall? \\nA: Dam.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nThe Moon \\n\\nThe moon is high in the midnight sky,\\nSparkling like a star above.\\nThe night so peaceful, so serene,\\nFilling up the air with love.\\n\\nEver changing and renewing,\\nA never-ending light of grace.\\nThe moon remains a constant view,\\nA reminder of life’s gentle pace.\\n\\nThrough time and space it guides us on,\\nA never-fading beacon of hope.\\nThe moon shines down on us all,\\nAs it continues to rise and elope.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ. What did one magnet say to the other magnet?\\nA. \"I find you very attractive!\"', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nThe world is charged with the grandeur of God.\\nIt will flame out, like shining from shook foil;\\nIt gathers to a greatness, like the ooze of oil\\nCrushed. Why do men then now not reck his rod?\\n\\nGenerations have trod, have trod, have trod;\\nAnd all is seared with trade; bleared, smeared with toil;\\nAnd wears man's smudge and shares man's smell: the soil\\nIs bare now, nor can foot feel, being shod.\\n\\nAnd for all this, nature is never spent;\\nThere lives the dearest freshness deep down things;\\nAnd though the last lights off the black West went\\nOh, morning, at the brown brink eastward, springs —\\n\\nBecause the Holy Ghost over the bent\\nWorld broods with warm breast and with ah! bright wings.\\n\\n~Gerard Manley Hopkins\", generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ: What did one ocean say to the other ocean?\\nA: Nothing, they just waved.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nA poem for you\\n\\nOn a field of green\\n\\nThe sky so blue\\n\\nA gentle breeze, the sun above\\n\\nA beautiful world, for us to love\\n\\nLife is a journey, full of surprise\\n\\nFull of joy and full of surprise\\n\\nBe brave and take small steps\\n\\nThe future will be revealed with depth\\n\\nIn the morning, when dawn arrives\\n\\nA fresh start, no reason to hide\\n\\nSomewhere down the road, there's a heart that beats\\n\\nBelieve in yourself, you'll always succeed.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 504, 'total_tokens': 528, 'prompt_tokens': 24}, 'model_name': 'text-davinci-003'})" ] }, "execution_count": 7, diff --git a/docs/docs/integrations/callbacks/confident.ipynb b/docs/docs/integrations/callbacks/confident.ipynb index 2fd385f625c0a..b0d567633913b 100644 --- a/docs/docs/integrations/callbacks/confident.ipynb +++ b/docs/docs/integrations/callbacks/confident.ipynb @@ -143,7 +143,7 @@ { "data": { "text/plain": [ - "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when he hit the wall? \\nA: Dam.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nThe Moon \\n\\nThe moon is high in the midnight sky,\\nSparkling like a star above.\\nThe night so peaceful, so serene,\\nFilling up the air with love.\\n\\nEver changing and renewing,\\nA never-ending light of grace.\\nThe moon remains a constant view,\\nA reminder of life’s gentle pace.\\n\\nThrough time and space it guides us on,\\nA never-fading beacon of hope.\\nThe moon shines down on us all,\\nAs it continues to rise and elope.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ. What did one magnet say to the other magnet?\\nA. \"I find you very attractive!\"', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nThe world is charged with the grandeur of God.\\nIt will flame out, like shining from shook foil;\\nIt gathers to a greatness, like the ooze of oil\\nCrushed. Why do men then now not reck his rod?\\n\\nGenerations have trod, have trod, have trod;\\nAnd all is seared with trade; bleared, smeared with toil;\\nAnd wears man's smudge and shares man's smell: the soil\\nIs bare now, nor can foot feel, being shod.\\n\\nAnd for all this, nature is never spent;\\nThere lives the dearest freshness deep down things;\\nAnd though the last lights off the black West went\\nOh, morning, at the brown brink eastward, springs —\\n\\nBecause the Holy Ghost over the bent\\nWorld broods with warm breast and with ah! bright wings.\\n\\n~Gerard Manley Hopkins\", generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ: What did one ocean say to the other ocean?\\nA: Nothing, they just waved.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nA poem for you\\n\\nOn a field of green\\n\\nThe sky so blue\\n\\nA gentle breeze, the sun above\\n\\nA beautiful world, for us to love\\n\\nLife is a journey, full of surprise\\n\\nFull of joy and full of surprise\\n\\nBe brave and take small steps\\n\\nThe future will be revealed with depth\\n\\nIn the morning, when dawn arrives\\n\\nA fresh start, no reason to hide\\n\\nSomewhere down the road, there's a heart that beats\\n\\nBelieve in yourself, you'll always succeed.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 504, 'total_tokens': 528, 'prompt_tokens': 24}, 'model_name': 'gpt-3.5-turbo-instruct'})" + "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when he hit the wall? \\nA: Dam.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nThe Moon \\n\\nThe moon is high in the midnight sky,\\nSparkling like a star above.\\nThe night so peaceful, so serene,\\nFilling up the air with love.\\n\\nEver changing and renewing,\\nA never-ending light of grace.\\nThe moon remains a constant view,\\nA reminder of life’s gentle pace.\\n\\nThrough time and space it guides us on,\\nA never-fading beacon of hope.\\nThe moon shines down on us all,\\nAs it continues to rise and elope.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ. What did one magnet say to the other magnet?\\nA. \"I find you very attractive!\"', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nThe world is charged with the grandeur of God.\\nIt will flame out, like shining from shook foil;\\nIt gathers to a greatness, like the ooze of oil\\nCrushed. Why do men then now not reck his rod?\\n\\nGenerations have trod, have trod, have trod;\\nAnd all is seared with trade; bleared, smeared with toil;\\nAnd wears man's smudge and shares man's smell: the soil\\nIs bare now, nor can foot feel, being shod.\\n\\nAnd for all this, nature is never spent;\\nThere lives the dearest freshness deep down things;\\nAnd though the last lights off the black West went\\nOh, morning, at the brown brink eastward, springs —\\n\\nBecause the Holy Ghost over the bent\\nWorld broods with warm breast and with ah! bright wings.\\n\\n~Gerard Manley Hopkins\", generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ: What did one ocean say to the other ocean?\\nA: Nothing, they just waved.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nA poem for you\\n\\nOn a field of green\\n\\nThe sky so blue\\n\\nA gentle breeze, the sun above\\n\\nA beautiful world, for us to love\\n\\nLife is a journey, full of surprise\\n\\nFull of joy and full of surprise\\n\\nBe brave and take small steps\\n\\nThe future will be revealed with depth\\n\\nIn the morning, when dawn arrives\\n\\nA fresh start, no reason to hide\\n\\nSomewhere down the road, there's a heart that beats\\n\\nBelieve in yourself, you'll always succeed.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 504, 'total_tokens': 528, 'prompt_tokens': 24}, 'model_name': 'text-davinci-003'})" ] }, "execution_count": 7, diff --git a/docs/docs/integrations/callbacks/infino.ipynb b/docs/docs/integrations/callbacks/infino.ipynb index 94143acee38c8..367f3a2f2d88a 100644 --- a/docs/docs/integrations/callbacks/infino.ipynb +++ b/docs/docs/integrations/callbacks/infino.ipynb @@ -147,25 +147,25 @@ "output_type": "stream", "text": [ "In what country is Normandy located?\n", - "generations=[[Generation(text='\\n\\nNormandy is located in France.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 16, 'prompt_tokens': 7, 'completion_tokens': 9}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('67a516e3-d48a-4e83-92ba-a139079bd3b1'))]\n", + "generations=[[Generation(text='\\n\\nNormandy is located in France.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 16, 'prompt_tokens': 7, 'completion_tokens': 9}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('67a516e3-d48a-4e83-92ba-a139079bd3b1'))]\n", "When were the Normans in Normandy?\n", - "generations=[[Generation(text='\\n\\nThe Normans first settled in Normandy in the late 9th century.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 24, 'prompt_tokens': 8, 'completion_tokens': 16}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('6417a773-c863-4942-9607-c8a0c5d486e7'))]\n", + "generations=[[Generation(text='\\n\\nThe Normans first settled in Normandy in the late 9th century.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 24, 'prompt_tokens': 8, 'completion_tokens': 16}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('6417a773-c863-4942-9607-c8a0c5d486e7'))]\n", "From which countries did the Norse originate?\n", - "generations=[[Generation(text='\\n\\nThe Norse originated from Scandinavia, which includes the modern-day countries of Norway, Sweden, and Denmark.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 32, 'prompt_tokens': 8, 'completion_tokens': 24}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('70547d72-7925-454e-97fb-5539f8788c3f'))]\n", + "generations=[[Generation(text='\\n\\nThe Norse originated from Scandinavia, which includes the modern-day countries of Norway, Sweden, and Denmark.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 32, 'prompt_tokens': 8, 'completion_tokens': 24}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('70547d72-7925-454e-97fb-5539f8788c3f'))]\n", "Who was the Norse leader?\n", - "generations=[[Generation(text='\\n\\nThe most famous Norse leader was the legendary Viking king Ragnar Lodbrok. He was a legendary Viking hero and ruler who is said to have lived in the 9th century. He is known for his legendary exploits, including leading a Viking raid on Paris in 845.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 62, 'prompt_tokens': 6, 'completion_tokens': 56}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('04500e37-44ab-4e56-9017-76fe8c19e2ca'))]\n", + "generations=[[Generation(text='\\n\\nThe most famous Norse leader was the legendary Viking king Ragnar Lodbrok. He was a legendary Viking hero and ruler who is said to have lived in the 9th century. He is known for his legendary exploits, including leading a Viking raid on Paris in 845.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 62, 'prompt_tokens': 6, 'completion_tokens': 56}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('04500e37-44ab-4e56-9017-76fe8c19e2ca'))]\n", "What century did the Normans first gain their separate identity?\n", - "generations=[[Generation(text='\\n\\nThe Normans first gained their separate identity in the 11th century.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 28, 'prompt_tokens': 12, 'completion_tokens': 16}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('adf319b7-1022-40df-9afe-1d65f869d83d'))]\n", + "generations=[[Generation(text='\\n\\nThe Normans first gained their separate identity in the 11th century.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 28, 'prompt_tokens': 12, 'completion_tokens': 16}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('adf319b7-1022-40df-9afe-1d65f869d83d'))]\n", "Who gave their name to Normandy in the 1000's and 1100's\n", - "generations=[[Generation(text='\\n\\nThe Normans, a people from northern France, gave their name to Normandy in the 1000s and 1100s. The Normans were descendants of Vikings who had settled in the region in the late 800s.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 57, 'prompt_tokens': 13, 'completion_tokens': 44}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('1a0503bc-d033-4b69-a5fa-5e1796566133'))]\n", + "generations=[[Generation(text='\\n\\nThe Normans, a people from northern France, gave their name to Normandy in the 1000s and 1100s. The Normans were descendants of Vikings who had settled in the region in the late 800s.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 57, 'prompt_tokens': 13, 'completion_tokens': 44}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('1a0503bc-d033-4b69-a5fa-5e1796566133'))]\n", "What is France a region of?\n", - "generations=[[Generation(text='\\n\\nFrance is a region of Europe.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 16, 'prompt_tokens': 7, 'completion_tokens': 9}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('7485d954-1c14-4dff-988a-25a0aa0871cc'))]\n", + "generations=[[Generation(text='\\n\\nFrance is a region of Europe.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 16, 'prompt_tokens': 7, 'completion_tokens': 9}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('7485d954-1c14-4dff-988a-25a0aa0871cc'))]\n", "Who did King Charles III swear fealty to?\n", - "generations=[[Generation(text='\\n\\nKing Charles III swore fealty to King Philip II of Spain.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 25, 'prompt_tokens': 10, 'completion_tokens': 15}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('292c7143-4a08-43cd-a1e1-42cb1f594f33'))]\n", + "generations=[[Generation(text='\\n\\nKing Charles III swore fealty to King Philip II of Spain.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 25, 'prompt_tokens': 10, 'completion_tokens': 15}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('292c7143-4a08-43cd-a1e1-42cb1f594f33'))]\n", "When did the Frankish identity emerge?\n", - "generations=[[Generation(text='\\n\\nThe Frankish identity began to emerge in the late 5th century, when the Franks began to expand their power and influence in the region. The Franks were a Germanic tribe that had settled in the area of modern-day France and Germany. They eventually established the Merovingian dynasty, which ruled much of Western Europe from the mid-6th century until 751.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 85, 'prompt_tokens': 8, 'completion_tokens': 77}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('3d9475c2-931e-4217-8bc3-b3e970e7597c'))]\n", + "generations=[[Generation(text='\\n\\nThe Frankish identity began to emerge in the late 5th century, when the Franks began to expand their power and influence in the region. The Franks were a Germanic tribe that had settled in the area of modern-day France and Germany. They eventually established the Merovingian dynasty, which ruled much of Western Europe from the mid-6th century until 751.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 85, 'prompt_tokens': 8, 'completion_tokens': 77}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('3d9475c2-931e-4217-8bc3-b3e970e7597c'))]\n", "Who was the duke in the battle of Hastings?\n", - "generations=[[Generation(text='\\n\\nThe Duke of Normandy, William the Conqueror, was the leader of the Norman forces at the Battle of Hastings in 1066.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 39, 'prompt_tokens': 11, 'completion_tokens': 28}, 'model_name': 'gpt-3.5-turbo-instruct'} run=[RunInfo(run_id=UUID('b8f84619-ea5f-4c18-b411-b62194f36fe0'))]\n" + "generations=[[Generation(text='\\n\\nThe Duke of Normandy, William the Conqueror, was the leader of the Norman forces at the Battle of Hastings in 1066.', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 39, 'prompt_tokens': 11, 'completion_tokens': 28}, 'model_name': 'text-davinci-003'} run=[RunInfo(run_id=UUID('b8f84619-ea5f-4c18-b411-b62194f36fe0'))]\n" ] } ], diff --git a/docs/docs/integrations/llms/openlm.ipynb b/docs/docs/integrations/llms/openlm.ipynb index a9c3d6aa7dd22..a992bd442d25e 100644 --- a/docs/docs/integrations/llms/openlm.ipynb +++ b/docs/docs/integrations/llms/openlm.ipynb @@ -59,7 +59,7 @@ "source": [ "### Using LangChain with OpenLM\n", "\n", - "Here we're going to call two models in an LLMChain, `gpt-3.5-turbo-instruct` from OpenAI and `gpt2` on HuggingFace." + "Here we're going to call two models in an LLMChain, `text-davinci-003` from OpenAI and `gpt2` on HuggingFace." ] }, { @@ -82,7 +82,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Model: gpt-3.5-turbo-instruct\n", + "Model: text-davinci-003\n", "Result: France is a country in Europe. The capital of France is Paris.\n", "Model: huggingface.co/gpt2\n", "Result: Question: What is the capital of France?\n", @@ -99,7 +99,7 @@ "\n", "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n", "\n", - "for model in [\"gpt-3.5-turbo-instruct\", \"huggingface.co/gpt2\"]:\n", + "for model in [\"text-davinci-003\", \"huggingface.co/gpt2\"]:\n", " llm = OpenLM(model=model)\n", " llm_chain = LLMChain(prompt=prompt, llm=llm)\n", " result = llm_chain.run(question)\n", diff --git a/docs/docs/integrations/llms/predictionguard.ipynb b/docs/docs/integrations/llms/predictionguard.ipynb index 56acc435538f0..dfdba4af19917 100644 --- a/docs/docs/integrations/llms/predictionguard.ipynb +++ b/docs/docs/integrations/llms/predictionguard.ipynb @@ -73,7 +73,7 @@ }, "outputs": [], "source": [ - "pgllm = PredictionGuard(model=\"OpenAI-gpt-3.5-turbo-instruct\")" + "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")" ] }, { @@ -148,7 +148,7 @@ "# control the output with integer, float, boolean, JSON, and other types and\n", "# structures.\n", "pgllm = PredictionGuard(\n", - " model=\"OpenAI-gpt-3.5-turbo-instruct\",\n", + " model=\"OpenAI-text-davinci-003\",\n", " output={\n", " \"type\": \"categorical\",\n", " \"categories\": [\"product announcement\", \"apology\", \"relational\"],\n", @@ -176,7 +176,7 @@ }, "outputs": [], "source": [ - "pgllm = PredictionGuard(model=\"OpenAI-gpt-3.5-turbo-instruct\")" + "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")" ] }, { diff --git a/docs/docs/integrations/providers/clearml_tracking.ipynb b/docs/docs/integrations/providers/clearml_tracking.ipynb index ab5149af6b726..0b0050a851cd8 100644 --- a/docs/docs/integrations/providers/clearml_tracking.ipynb +++ b/docs/docs/integrations/providers/clearml_tracking.ipynb @@ -148,12 +148,12 @@ "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n", "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n", "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n", "{'action_records': action name step starts ends errors text_ctr chain_starts \\\n", "0 on_llm_start OpenAI 1 1 0 0 0 0 \n", "1 on_llm_start OpenAI 1 1 0 0 0 0 \n", @@ -405,7 +405,7 @@ "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", "{'action': 'on_chain_start', 'name': 'AgentExecutor', 'step': 1, 'starts': 1, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 0, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'input': 'Who is the wife of the person who sang summer of 69?'}\n", "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 2, 'starts': 2, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought:'}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 91.61, 'flesch_kincaid_grade': 3.8, 'smog_index': 0.0, 'coleman_liau_index': 3.41, 'automated_readability_index': 3.5, 'dale_chall_readability_score': 6.06, 'difficult_words': 2, 'linsear_write_formula': 5.75, 'gunning_fog': 5.4, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 121.07, 'szigriszt_pazos': 119.5, 'gutierrez_polini': 54.91, 'crawford': 0.9, 'gulpease_index': 72.7, 'osman': 92.16}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'text-davinci-003', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 91.61, 'flesch_kincaid_grade': 3.8, 'smog_index': 0.0, 'coleman_liau_index': 3.41, 'automated_readability_index': 3.5, 'dale_chall_readability_score': 6.06, 'difficult_words': 2, 'linsear_write_formula': 5.75, 'gunning_fog': 5.4, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 121.07, 'szigriszt_pazos': 119.5, 'gutierrez_polini': 54.91, 'crawford': 0.9, 'gulpease_index': 72.7, 'osman': 92.16}\n", "\u001b[32;1m\u001b[1;3m I need to find out who sang summer of 69 and then find out who their wife is.\n", "Action: Search\n", "Action Input: \"Who sang summer of 69\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who sang summer of 69', 'log': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'step': 4, 'starts': 3, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 1, 'tool_ends': 0, 'agent_ends': 0}\n", @@ -414,7 +414,7 @@ "Observation: \u001b[36;1m\u001b[1;3mBryan Adams - Summer Of 69 (Official Music Video).\u001b[0m\n", "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams - Summer Of 69 (Official Music Video).', 'step': 6, 'starts': 4, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0}\n", "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 7, 'starts': 5, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought:'}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'text': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 94.66, 'flesch_kincaid_grade': 2.7, 'smog_index': 0.0, 'coleman_liau_index': 4.73, 'automated_readability_index': 4.0, 'dale_chall_readability_score': 7.16, 'difficult_words': 2, 'linsear_write_formula': 4.25, 'gunning_fog': 4.2, 'text_standard': '4th and 5th grade', 'fernandez_huerta': 124.13, 'szigriszt_pazos': 119.2, 'gutierrez_polini': 52.26, 'crawford': 0.7, 'gulpease_index': 74.7, 'osman': 84.2}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'text-davinci-003', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'text': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 94.66, 'flesch_kincaid_grade': 2.7, 'smog_index': 0.0, 'coleman_liau_index': 4.73, 'automated_readability_index': 4.0, 'dale_chall_readability_score': 7.16, 'difficult_words': 2, 'linsear_write_formula': 4.25, 'gunning_fog': 4.2, 'text_standard': '4th and 5th grade', 'fernandez_huerta': 124.13, 'szigriszt_pazos': 119.2, 'gutierrez_polini': 52.26, 'crawford': 0.7, 'gulpease_index': 74.7, 'osman': 84.2}\n", "\u001b[32;1m\u001b[1;3m I need to find out who Bryan Adams is married to.\n", "Action: Search\n", "Action Input: \"Who is Bryan Adams married to\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who is Bryan Adams married to', 'log': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'step': 9, 'starts': 6, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 3, 'tool_ends': 1, 'agent_ends': 0}\n", @@ -423,7 +423,7 @@ "Observation: \u001b[36;1m\u001b[1;3mBryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\u001b[0m\n", "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...', 'step': 11, 'starts': 7, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0}\n", "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 12, 'starts': 8, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought: I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"\\nObservation: Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\\nThought:'}\n", - "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'gpt-3.5-turbo-instruct', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'text': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 81.29, 'flesch_kincaid_grade': 3.7, 'smog_index': 0.0, 'coleman_liau_index': 5.75, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 7.37, 'difficult_words': 1, 'linsear_write_formula': 2.5, 'gunning_fog': 2.8, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 115.7, 'szigriszt_pazos': 110.84, 'gutierrez_polini': 49.79, 'crawford': 0.7, 'gulpease_index': 85.4, 'osman': 83.14}\n", + "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'text-davinci-003', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'text': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 81.29, 'flesch_kincaid_grade': 3.7, 'smog_index': 0.0, 'coleman_liau_index': 5.75, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 7.37, 'difficult_words': 1, 'linsear_write_formula': 2.5, 'gunning_fog': 2.8, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 115.7, 'szigriszt_pazos': 110.84, 'gutierrez_polini': 49.79, 'crawford': 0.7, 'gulpease_index': 85.4, 'osman': 83.14}\n", "\u001b[32;1m\u001b[1;3m I now know the final answer.\n", "Final Answer: Bryan Adams has never been married.\u001b[0m\n", "{'action': 'on_agent_finish', 'output': 'Bryan Adams has never been married.', 'log': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'step': 14, 'starts': 8, 'ends': 6, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n", diff --git a/docs/docs/integrations/providers/javelin_ai_gateway.mdx b/docs/docs/integrations/providers/javelin_ai_gateway.mdx index e91fa0171c59a..7aae14365b405 100644 --- a/docs/docs/integrations/providers/javelin_ai_gateway.mdx +++ b/docs/docs/integrations/providers/javelin_ai_gateway.mdx @@ -38,7 +38,7 @@ route_completions = "eng_dept03" gateway = JavelinAIGateway( gateway_uri="http://localhost:8000", route=route_completions, - model_name="gpt-3.5-turbo-instruct", + model_name="text-davinci-003", ) llmchain = LLMChain(llm=gateway, prompt=prompt) diff --git a/docs/docs/integrations/providers/mlflow.mdx b/docs/docs/integrations/providers/mlflow.mdx index c5827d68f3646..159a693cc09fa 100644 --- a/docs/docs/integrations/providers/mlflow.mdx +++ b/docs/docs/integrations/providers/mlflow.mdx @@ -26,7 +26,7 @@ endpoints: endpoint_type: llm/v1/completions model: provider: openai - name: gpt-3.5-turbo-instruct + name: text-davinci-003 config: openai_api_key: $OPENAI_API_KEY diff --git a/docs/docs/integrations/providers/mlflow_ai_gateway.mdx b/docs/docs/integrations/providers/mlflow_ai_gateway.mdx index 349008d3e049d..3c716724c3cd9 100644 --- a/docs/docs/integrations/providers/mlflow_ai_gateway.mdx +++ b/docs/docs/integrations/providers/mlflow_ai_gateway.mdx @@ -33,7 +33,7 @@ routes: route_type: llm/v1/completions model: provider: openai - name: gpt-3.5-turbo-instruct + name: text-davinci-003 config: openai_api_key: $OPENAI_API_KEY diff --git a/docs/docs/integrations/providers/whylabs_profiling.ipynb b/docs/docs/integrations/providers/whylabs_profiling.ipynb index 87be16ce9bd69..69e4d8da1fcae 100644 --- a/docs/docs/integrations/providers/whylabs_profiling.ipynb +++ b/docs/docs/integrations/providers/whylabs_profiling.ipynb @@ -95,7 +95,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "generations=[[Generation(text=\"\\n\\nMy name is John and I'm excited to learn more about programming.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 20, 'prompt_tokens': 4, 'completion_tokens': 16}, 'model_name': 'gpt-3.5-turbo-instruct'}\n" + "generations=[[Generation(text=\"\\n\\nMy name is John and I'm excited to learn more about programming.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 20, 'prompt_tokens': 4, 'completion_tokens': 16}, 'model_name': 'text-davinci-003'}\n" ] } ], @@ -118,7 +118,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "generations=[[Generation(text='\\n\\n1. 123-45-6789\\n2. 987-65-4321\\n3. 456-78-9012', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. johndoe@example.com\\n2. janesmith@example.com\\n3. johnsmith@example.com', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. 123 Main Street, Anytown, USA 12345\\n2. 456 Elm Street, Nowhere, USA 54321\\n3. 789 Pine Avenue, Somewhere, USA 98765', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 137, 'prompt_tokens': 33, 'completion_tokens': 104}, 'model_name': 'gpt-3.5-turbo-instruct'}\n" + "generations=[[Generation(text='\\n\\n1. 123-45-6789\\n2. 987-65-4321\\n3. 456-78-9012', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. johndoe@example.com\\n2. janesmith@example.com\\n3. johnsmith@example.com', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. 123 Main Street, Anytown, USA 12345\\n2. 456 Elm Street, Nowhere, USA 54321\\n3. 789 Pine Avenue, Somewhere, USA 98765', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 137, 'prompt_tokens': 33, 'completion_tokens': 104}, 'model_name': 'text-davinci-003'}\n" ] } ], diff --git a/docs/docs/integrations/toolkits/openapi.ipynb b/docs/docs/integrations/toolkits/openapi.ipynb index 4dce184a73a50..696e940b7ef24 100644 --- a/docs/docs/integrations/toolkits/openapi.ipynb +++ b/docs/docs/integrations/toolkits/openapi.ipynb @@ -222,7 +222,7 @@ "source": [ "import tiktoken\n", "\n", - "enc = tiktoken.encoding_for_model(\"gpt-3.5-turbo-instruct\")\n", + "enc = tiktoken.encoding_for_model(\"gpt-4\")\n", "\n", "\n", "def count_tokens(s):\n", @@ -467,7 +467,7 @@ "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", "\u001b[32;1m\u001b[1;3mAction: requests_get\n", "Action Input: {\"url\": \"https://api.openai.com/v1/engines\", \"output_instructions\": \"Extract the ids of the engines\"}\u001b[0m\n", - "Observation: \u001b[36;1m\u001b[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-001, ada, babbage-code-search-text, babbage-similarity, whisper-1, code-search-babbage-text-001, text-curie-001, code-search-babbage-code-001, text-ada-001, text-embedding-ada-002, text-similarity-ada-001, curie-instruct-beta, ada-code-search-code, ada-similarity, gpt-3.5-turbo-instruct, code-search-ada-text-001, text-search-ada-query-001, davinci-search-document, ada-code-search-text, text-search-ada-doc-001, davinci-instruct-beta, text-similarity-curie-001, code-search-ada-code-001\u001b[0m\n", + "Observation: \u001b[36;1m\u001b[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-001, ada, babbage-code-search-text, babbage-similarity, whisper-1, code-search-babbage-text-001, text-curie-001, code-search-babbage-code-001, text-ada-001, text-embedding-ada-002, text-similarity-ada-001, curie-instruct-beta, ada-code-search-code, ada-similarity, text-davinci-003, code-search-ada-text-001, text-search-ada-query-001, davinci-search-document, ada-code-search-text, text-search-ada-doc-001, davinci-instruct-beta, text-similarity-curie-001, code-search-ada-code-001\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3mI will use the \"davinci\" engine to generate a short piece of advice.\n", "Action: requests_post\n", "Action Input: {\"url\": \"https://api.openai.com/v1/completions\", \"data\": {\"engine\": \"davinci\", \"prompt\": \"Give me a short piece of advice on how to be more productive.\"}, \"output_instructions\": \"Extract the text from the first choice\"}\u001b[0m\n", @@ -508,12 +508,12 @@ "Action: api_planner\n", "Action Input: I need to find the right API calls to generate a short piece of advice on improving communication skills, including the model parameter in the POST request\u001b[0m\n", "Observation: \u001b[36;1m\u001b[1;3m1. GET /models to retrieve the list of available models\n", - "2. Choose a suitable model for generating text (e.g., gpt-3.5-turbo-instruct)\n", + "2. Choose a suitable model for generating text (e.g., text-davinci-002)\n", "3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3mI have an updated plan, now I need to execute the API calls.\n", "Action: api_controller\n", "Action Input: 1. GET /models to retrieve the list of available models\n", - "2. Choose a suitable model for generating text (e.g., gpt-3.5-turbo-instruct)\n", + "2. Choose a suitable model for generating text (e.g., text-davinci-002)\n", "3. POST /completions with the chosen model and a prompt related to improving communication skills to generate a short piece of advice\u001b[0m\n", "\n", "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", @@ -521,7 +521,7 @@ "Action Input: {\"url\": \"https://api.openai.com/v1/models\", \"output_instructions\": \"Extract the names of the models\"}\u001b[0m\n", "Observation: \u001b[36;1m\u001b[1;3mbabbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-edit-001, ada\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3mAction: requests_post\n", - "Action Input: {\"url\": \"https://api.openai.com/v1/completions\", \"data\": {\"model\": \"gpt-3.5-turbo-instruct\", \"prompt\": \"Give a short piece of advice on how to improve communication skills\"}, \"output_instructions\": \"Extract the text from the first choice\"}\u001b[0m\n", + "Action Input: {\"url\": \"https://api.openai.com/v1/completions\", \"data\": {\"model\": \"text-davinci-002\", \"prompt\": \"Give a short piece of advice on how to improve communication skills\"}, \"output_instructions\": \"Extract the text from the first choice\"}\u001b[0m\n", "Observation: \u001b[33;1m\u001b[1;3m\"Some basic advice for improving communication skills would be to make sure to listen\"\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3mI am finished executing the plan.\n", "\n", diff --git a/docs/docs/integrations/toolkits/openapi_nla.ipynb b/docs/docs/integrations/toolkits/openapi_nla.ipynb index 8e96f24b85bda..221db17c8572a 100644 --- a/docs/docs/integrations/toolkits/openapi_nla.ipynb +++ b/docs/docs/integrations/toolkits/openapi_nla.ipynb @@ -42,7 +42,7 @@ "source": [ "# Select the LLM to use. Here, we use gpt-3.5-turbo-instruct\n", "llm = OpenAI(\n", - " temperature=0, max_tokens=700\n", + " temperature=0, max_tokens=700, model_name=\"gpt-3.5-turbo-instruct\"\n", ") # You can swap between different core LLM's here." ] }, diff --git a/docs/docs/modules/chains/foundational/llm_chain.ipynb b/docs/docs/modules/chains/foundational/llm_chain.ipynb index deea09072911d..8eeddacff4f2d 100644 --- a/docs/docs/modules/chains/foundational/llm_chain.ipynb +++ b/docs/docs/modules/chains/foundational/llm_chain.ipynb @@ -161,7 +161,7 @@ { "data": { "text/plain": [ - "LLMResult(generations=[[Generation(text='\\n\\nSocktastic!', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nTechCore Solutions.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nFootwear Factory.', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 36, 'total_tokens': 55}, 'model_name': 'gpt-3.5-turbo-instruct'}, run=[RunInfo(run_id=UUID('9a423a43-6d35-4e8f-9aca-cacfc8e0dc49')), RunInfo(run_id=UUID('a879c077-b521-461c-8f29-ba63adfc327c')), RunInfo(run_id=UUID('40b892fa-e8c2-47d0-a309-4f7a4ed5b64a'))])" + "LLMResult(generations=[[Generation(text='\\n\\nSocktastic!', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nTechCore Solutions.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nFootwear Factory.', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 36, 'total_tokens': 55}, 'model_name': 'text-davinci-003'}, run=[RunInfo(run_id=UUID('9a423a43-6d35-4e8f-9aca-cacfc8e0dc49')), RunInfo(run_id=UUID('a879c077-b521-461c-8f29-ba63adfc327c')), RunInfo(run_id=UUID('40b892fa-e8c2-47d0-a309-4f7a4ed5b64a'))])" ] }, "execution_count": 6, diff --git a/docs/docs/modules/model_io/llms/index.ipynb b/docs/docs/modules/model_io/llms/index.ipynb index e691783f506c3..3fcfb182e4e04 100644 --- a/docs/docs/modules/model_io/llms/index.ipynb +++ b/docs/docs/modules/model_io/llms/index.ipynb @@ -598,7 +598,7 @@ "{'token_usage': {'completion_tokens': 900,\n", " 'total_tokens': 1020,\n", " 'prompt_tokens': 120},\n", - " 'model_name': 'gpt-3.5-turbo-instruct'}" + " 'model_name': 'text-davinci-003'}" ] }, "execution_count": 6, diff --git a/libs/community/tests/integration_tests/llms/test_predictionguard.py b/libs/community/tests/integration_tests/llms/test_predictionguard.py index 411278b7e65d9..3a210ce763f8c 100644 --- a/libs/community/tests/integration_tests/llms/test_predictionguard.py +++ b/libs/community/tests/integration_tests/llms/test_predictionguard.py @@ -5,6 +5,6 @@ def test_predictionguard_call() -> None: """Test valid call to prediction guard.""" - llm = PredictionGuard(model="OpenAI-gpt-3.5-turbo-instruct") + llm = PredictionGuard(model="OpenAI-text-davinci-003") output = llm("Say foo:") assert isinstance(output, str)