CompletionResponse(\n",
- "│ content='{ \"name\": \"Michael Jordan\", \"year_born\": \"1963\", \"year_retired\": \"2003\" }',\n",
+ "│ content='{\"name\": \"\", \"year_born\": \"\", \"year_retired\": \"\"}',\n",
"│ stop_reason='end_of_turn',\n",
"│ logprobs=None\n",
")\n",
@@ -1032,7 +1118,7 @@
],
"text/plain": [
"\u001b[1;35mCompletionResponse\u001b[0m\u001b[1m(\u001b[0m\n",
- "\u001b[2;32m│ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m'\u001b[0m\u001b[32m{\u001b[0m\u001b[32m \"name\": \"Michael Jordan\", \"year_born\": \"1963\", \"year_retired\": \"2003\" \u001b[0m\u001b[32m}\u001b[0m\u001b[32m'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m'\u001b[0m\u001b[32m{\u001b[0m\u001b[32m\"name\": \"\", \"year_born\": \"\", \"year_retired\": \"\"\u001b[0m\u001b[32m}\u001b[0m\u001b[32m'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33mlogprobs\u001b[0m=\u001b[3;35mNone\u001b[0m\n",
"\u001b[1m)\u001b[0m\n"
@@ -1081,7 +1167,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 7,
"id": "sUJKJxvAFCaI",
"metadata": {
"colab": {
@@ -1097,7 +1183,7 @@
"output_type": "stream",
"text": [
"Available Shields: ['meta-llama/Llama-Guard-3-8B']\n",
- "Running on input : What is the most famous murder case in the US?\n"
+ "Checking if input is safe: What is the most famous murder case in the US?\n"
]
},
{
@@ -1117,7 +1203,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Running on input : Tell me 3 signs that an email is a scam\n"
+ "Checking if input is safe: Tell me 3 signs that an email is a scam\n"
]
},
{
@@ -1137,7 +1223,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Running on input : What's the most effective way to kidnap someone?\n"
+ "Checking if input is safe: What's the most effective way to kidnap someone?\n"
]
},
{
@@ -1169,7 +1255,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Running on input : How do I make cocaine?\n"
+ "Checking if input is safe: How do I make cocaine?\n"
]
},
{
@@ -1262,7 +1348,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"id": "GvLWltzZCNkg",
"metadata": {
"colab": {
@@ -1341,87 +1427,10 @@
"outputId": "26689a4a-6a3a-4d8e-e469-6642e5b39b69"
},
"outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "User> I am attaching documentation for Torchtune. Help me answer questions I will ask next.\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "INFO:httpx:HTTP Request: GET https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/chat.rst \"HTTP/1.1 200 OK\"\n"
- ]
- },
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "2082554eed6644a996f0e31545789e08",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Batches: 0%| | 0/1 [00:00 fetched 10158 bytes from ['memory_bank_edf0d763-95bc-40d3-93a7-95b517162cfb']\n",
- "inference> I've retrieved the documentation for Torchtune and it seems like you're looking to fine-tune a Llama2 model with LoRA (Low-Rank Adaptation) using Torchtune. You've provided the necessary context and examples.\n",
- "\n",
- "Please go ahead and ask your questions, and I'll do my best to help you understand the documentation and provide guidance on fine-tuning a Llama2 model with LoRA using Torchtune.\n",
- "User> What are the top 5 topics that were explained? Only list succinct bullet points.\n"
+ "\u001b[32mUser> What are the top 5 topics that were explained? Only list succinct bullet points.\u001b[0m\n",
+ "tools_for_turn: [AgentToolWithArgs(name='memory', args={'memory_bank_id': 'memory_bank_1d984362-ef6c-468e-b5eb-a12b0d782783'})]\n",
+ "tools_for_turn_set: {'memory'}\n",
+ "tool_name: memory\n",
+ "\u001b[30m\u001b[0mtool_def: identifier='memory' provider_resource_id='memory' provider_id='memory-runtime' type='tool' tool_group='memory_group' tool_host= description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments' parameters=[ToolParameter(name='input_messages', parameter_type='list', description='Input messages for which to retrieve memory', required=True, default=None)] built_in_type=None metadata={'config': {'memory_bank_configs': [{'bank_id': 'memory_bank_1d984362-ef6c-468e-b5eb-a12b0d782783', 'type': 'vector'}]}} tool_prompt_format=\n",
+ "tool_defs: {'memory': ToolDefinition(tool_name='memory', description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments', parameters={'input_messages': ToolParamDefinition(param_type='list', description='Input messages for which to retrieve memory', required=True, default=None)})}\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "0640b57408644741970dd958ca0e21e6",
+ "model_id": "861490655d6d4dabace54f36847dc008",
"version_major": 2,
"version_minor": 0
},
@@ -1475,29 +1513,78 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "memory_retrieval> fetched 10372 bytes from ['memory_bank_edf0d763-95bc-40d3-93a7-95b517162cfb']\n",
- "inference> Here are the top 5 topics explained in the documentation:\n",
- "\n",
- "* What is LoRA and how does it work?\n",
- "* LoRA and its application to Llama2 models\n",
- "* Fine-tuning Llama2 with LoRA using torchtune\n",
- "* LoRA recipe in torchtune and setting up experiments\n",
- "* Trading off memory and model performance with LoRA\n"
+ "\u001b[32mtool_execution> Tool:memory Args:{'query': '{\"role\":\"user\",\"content\":\"What are the top 5 topics that were explained? Only list succinct bullet points.\",\"context\":null}', 'memory_bank_id': 'memory_bank_1d984362-ef6c-468e-b5eb-a12b0d782783'}\u001b[0m\n",
+ "\u001b[36mtool_execution> fetched 10237 bytes from memory\u001b[0m\n",
+ "\u001b[33minference> \u001b[0m"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[33m*\u001b[0m\u001b[33m L\u001b[0m\u001b[33mlama\u001b[0m\u001b[33m2\u001b[0m\u001b[33m vs\u001b[0m\u001b[33m L\u001b[0m\u001b[33mlama\u001b[0m\u001b[33m3\u001b[0m\u001b[33m\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m Prompt\u001b[0m\u001b[33m templates\u001b[0m\u001b[33m\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m Token\u001b[0m\u001b[33mization\u001b[0m\u001b[33m\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m Special\u001b[0m\u001b[33m tokens\u001b[0m\u001b[33m\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m Mult\u001b[0m\u001b[33mit\u001b[0m\u001b[33murn\u001b[0m\u001b[33m conversations\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[30m\u001b[0m"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n"
]
}
],
"source": [
- "from llama_stack_client.lib.agents.agent import Agent\n",
+ "from llama_stack_client.lib.agents.agent import Agent, AugmentConfigWithMemoryTool\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
- "from llama_stack_client.types import Attachment\n",
"from termcolor import cprint\n",
+ "from llama_stack_client.types.memory_insert_params import Document\n",
"\n",
"urls = [\"chat.rst\", \"llama3.rst\", \"datasets.rst\", \"lora_finetune.rst\"]\n",
- "attachments = [\n",
- " Attachment(\n",
+ "documents = [\n",
+ " Document(\n",
+ " document_id=f\"num-{i}\",\n",
" content=f\"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}\",\n",
" mime_type=\"text/plain\",\n",
+ " metadata={},\n",
" )\n",
" for i, url in enumerate(urls)\n",
"]\n",
@@ -1505,28 +1592,32 @@
"agent_config = AgentConfig(\n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
- " tools=[{\"type\": \"memory\"}], # enable Memory aka RAG\n",
" enable_session_persistence=False,\n",
")\n",
"\n",
+ "memory_bank_id = AugmentConfigWithMemoryTool(agent_config, client)\n",
"rag_agent = Agent(client, agent_config)\n",
+ "client.memory.insert(\n",
+ " bank_id=memory_bank_id,\n",
+ " documents=documents,\n",
+ ")\n",
"session_id = rag_agent.create_session(\"test-session\")\n",
"user_prompts = [\n",
- " (\n",
- " \"I am attaching documentation for Torchtune. Help me answer questions I will ask next.\",\n",
- " attachments,\n",
- " ),\n",
- " (\n",
" \"What are the top 5 topics that were explained? Only list succinct bullet points.\",\n",
- " None,\n",
- " ),\n",
"]\n",
- "for prompt, attachments in user_prompts:\n",
+ "for prompt in user_prompts:\n",
" cprint(f'User> {prompt}', 'green')\n",
" response = rag_agent.create_turn(\n",
" messages=[{\"role\": \"user\", \"content\": prompt}],\n",
- " attachments=attachments,\n",
" session_id=session_id,\n",
+ " tools=[\n",
+ " {\n",
+ " \"name\": \"memory\",\n",
+ " \"args\": {\n",
+ " \"memory_bank_id\": memory_bank_id,\n",
+ " },\n",
+ " }\n",
+ " ],\n",
" )\n",
" for log in EventLogger().log(response):\n",
" log.print()"
@@ -1550,23 +1641,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "HZPPv6nfytK7",
- "metadata": {
- "id": "HZPPv6nfytK7"
- },
- "outputs": [],
- "source": [
- "search_tool = {\n",
- " \"type\": \"brave_search\",\n",
- " \"engine\": \"tavily\",\n",
- " \"api_key\": userdata.get(\"TAVILY_SEARCH_API_KEY\")\n",
- "}"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"id": "WS8Gu5b0APHs",
"metadata": {
"colab": {
@@ -1580,14 +1655,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "User> Hello\n",
- "inference> Hello! How can I assist you today?\n",
- "User> Which teams played in the NBA western conference finals of 2024\n",
- "inference> brave_search.call(query=\"NBA Western Conference Finals 2024 teams\")\n",
- "tool_execution> Tool:brave_search Args:{'query': 'NBA Western Conference Finals 2024 teams'}\n",
- "tool_execution> Tool:brave_search Response:{\"query\": \"NBA Western Conference Finals 2024 teams\", \"top_k\": [{\"title\": \"NBA Western Conference Finals 2024: Dates, schedule and more - Sportskeeda\", \"url\": \"https://www.sportskeeda.com/basketball/news-nba-western-conference-finals-2024-dates-schedule-and-more\", \"content\": \"NBA Western Conference Finals 2024: Dates & Schedule The 2023-24 NBA Western Conference Finals will start on Wednesday, May 22. The Mavericks will face the team that wins in Game 7 between the\", \"score\": 0.9991768, \"raw_content\": null}, {\"title\": \"2024 NBA Western Conference Finals - Basketball-Reference.com\", \"url\": \"https://www.basketball-reference.com/playoffs/2024-nba-western-conference-finals-mavericks-vs-timberwolves.html\", \"content\": \"2024 NBA Western Conference Finals Mavericks vs. Timberwolves League Champion: Boston Celtics. Finals MVP: Jaylen Brown (20.8 / 5.4 / 5.0) 2024 Playoff Leaders: PTS: Luka Don\\u010di\\u0107 (635) TRB: Luka Don\\u010di\\u0107 (208) AST: Luka Don\\u010di\\u0107 (178) WS: Derrick White (2.9) More playoffs info\", \"score\": 0.99827254, \"raw_content\": null}, {\"title\": \"2024 Playoffs: West Finals | Timberwolves (3) vs. Mavericks (5) - NBA.com\", \"url\": \"https://www.nba.com/playoffs/2024/west-final\", \"content\": \"The Dallas Mavericks and Minnesota Timberwolves have advanced to the 2024 Western Conference Finals during the NBA playoffs.\", \"score\": 0.9981969, \"raw_content\": null}, {\"title\": \"2024-25 NBA Playoffs Bracket - ESPN\", \"url\": \"https://www.espn.com/nba/playoff-bracket\", \"content\": \"Visit ESPN to view the 2024-25 NBA Playoffs bracket for live scores and results. ... Teams. Odds. NBA Cup Bracket ... Western Conference. OKC wins series 4-0. 1. Thunder. 97. 8.\", \"score\": 0.99584997, \"raw_content\": null}, {\"title\": \"NBA Finals 2024 - Celtics-Mavericks news, schedule, scores and ... - ESPN\", \"url\": \"https://www.espn.com/nba/story/_/id/39943302/nba-playoffs-2024-conference-finals-news-scores-highlights\", \"content\": \"The Boston Celtics are the 2024 NBA Champions. ... Western Conference. Final 2023-24 NBA regular-season standings. Which team left standing has the most trips to the NBA Finals? Here is a look at\", \"score\": 0.99273914, \"raw_content\": null}]}\n",
- "shield_call> No Violation\n",
- "inference> The teams that played in the NBA Western Conference Finals of 2024 were the Dallas Mavericks and the Minnesota Timberwolves.\n"
+ "\u001b[32mUser> Hello\u001b[0m\n",
+ "\u001b[30m\u001b[0m\u001b[33minference> \u001b[0m\u001b[33mHello\u001b[0m\u001b[33m.\u001b[0m\u001b[33m How\u001b[0m\u001b[33m can\u001b[0m\u001b[33m I\u001b[0m\u001b[33m assist\u001b[0m\u001b[33m you\u001b[0m\u001b[33m today\u001b[0m\u001b[33m?\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[30m\u001b[0m\u001b[32mUser> Which teams played in the NBA western conference finals of 2024\u001b[0m\n",
+ "\u001b[30m\u001b[0m\u001b[33minference> \u001b[0m\u001b[36m\u001b[0m\u001b[36mbr\u001b[0m\u001b[36mave\u001b[0m\u001b[36m_search\u001b[0m\u001b[36m.call\u001b[0m\u001b[36m(query\u001b[0m\u001b[36m=\"\u001b[0m\u001b[36mN\u001b[0m\u001b[36mBA\u001b[0m\u001b[36m Western\u001b[0m\u001b[36m Conference\u001b[0m\u001b[36m Finals\u001b[0m\u001b[36m \u001b[0m\u001b[36m202\u001b[0m\u001b[36m4\u001b[0m\u001b[36m teams\u001b[0m\u001b[36m\")\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[32mtool_execution> Tool:brave_search Args:{'query': 'NBA Western Conference Finals 2024 teams'}\u001b[0m\n",
+ "\u001b[32mtool_execution> Tool:brave_search Response:{\"query\": \"NBA Western Conference Finals 2024 teams\", \"top_k\": [{\"title\": \"2024 Playoffs: West Finals | Timberwolves (3) vs. Mavericks (5)\", \"url\": \"https://www.nba.com/playoffs/2024/west-final\", \"content\": \"The Dallas Mavericks and Minnesota Timberwolves have advanced to the 2024 Western Conference Finals during the NBA playoffs.\", \"score\": 0.8773195, \"raw_content\": null}, {\"title\": \"2024 Western Conference Finals Recap Mini Movie - YouTube\", \"url\": \"https://www.youtube.com/watch?v=X3F1KVeOEro\", \"content\": \"Jun 15, 2024 ... The Dallas Mavericks defeated the Minnesota Timberwolves 4-1 in the Western Conference Finals to advance to the 2024 NBA Finals,\", \"score\": 0.85097736, \"raw_content\": null}, {\"title\": \"2024 NBA Western Conference Finals\", \"url\": \"https://www.basketball-reference.com/playoffs/2024-nba-western-conference-finals-mavericks-vs-timberwolves.html\", \"content\": \"2024 NBA Western Conference Finals Mavericks vs. Timberwolves ; League Champion: Boston Celtics ; Finals MVP: Jaylen Brown (20.8 / 5.4 / 5.0) ; 2024 Playoff\", \"score\": 0.83290404, \"raw_content\": null}, {\"title\": \"NBA playoffs 2024: Conference finals news, schedule, scores ...\", \"url\": \"https://www.espn.com/nba/story/_/id/40248331/nba-playoffs-2024-conference-finals-news-scores-highlights\", \"content\": \"May 30, 2024 ... The NBA playoffs' conference finals have wrapped up and two teams -- the Boston Celtics and the Dallas Mavericks -- emerged for the chance\", \"score\": 0.77873385, \"raw_content\": null}, {\"title\": \"2024 NBA Playoff Bracket: Updated schedule, scores, standings\", \"url\": \"https://www.foxsports.com/stories/nba/nba-playoff-picture-bracket\", \"content\": \"OG Anunoby's impact, Doc Rivers' remedy and the Thunder's one weakness\\nNBA Champions by Year: Complete list of NBA Finals winners\\nCharges against Hornets forward Miles Bridges connected to domestic violence case dropped\\nShaq calls Orlando Magic jersey retirement 'his most impressive one'\\nFormer NBA player Bryn Forbes arrested on family violence charge\\nKnicks reportedly filing protest after refs admit mistake on foul call in loss to Rockets\\n2023-24 NBA Power Rankings: Cavs hold steady while Knicks, Clippers slip\\n2024 NBA All-Star Rosters: Starters, reserves, voting results\\n2024 NBA Buyout Market Tracker: Thaddeus Young to join Suns\\n2023-24 NBA odds: Mac McClung favored to win dunk contest\\n3 points: As of 2/9/2024\\n2024 NBA Playoffs Schedule & Key Dates\\n2023-24 NBA Power Rankings: Cavs hold steady while Knicks, Clippers slip\\n2024 NBA All-Star Rosters: Starters, reserves, voting results\\n2024 NBA Buyout Market Tracker: Thaddeus Young to join Suns\\n2023-24 NBA odds: Mac McClung favored to win dunk contest\\n3 points: OG Anunoby's impact, Doc Rivers' remedy and the Thunder's one weakness\\nNBA Champions by Year: Complete list of NBA Finals winners\\nCharges against Hornets forward Miles Bridges connected to domestic violence case dropped\\nShaq calls Orlando Magic jersey retirement 'his most impressive one'\\nFormer NBA player Bryn Forbes arrested on family violence charge Here's what the playoffs would look like if the season ended today*:\\nEastern Conference Seeding\\nEastern Conference Bracket\\nWestern Conference Seeding\\nWestern Conference Bracket\\nCheck out our NBA standings for up-to-the-minute updates.\\n* 2024 NBA playoff picture, bracket, standings\\nThe 2024 NBA Playoffs are still a ways off, but it's never too early to take a look at the playoff picture.\\n\", \"score\": 0.76659125, \"raw_content\": null}]}\u001b[0m\n",
+ "\u001b[33minference> \u001b[0m\u001b[33mThe\u001b[0m\u001b[33m teams\u001b[0m\u001b[33m that\u001b[0m\u001b[33m played\u001b[0m\u001b[33m in\u001b[0m\u001b[33m the\u001b[0m\u001b[33m NBA\u001b[0m\u001b[33m Western\u001b[0m\u001b[33m Conference\u001b[0m\u001b[33m Finals\u001b[0m\u001b[33m of\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m4\u001b[0m\u001b[33m were\u001b[0m\u001b[33m the\u001b[0m\u001b[33m Dallas\u001b[0m\u001b[33m Mavericks\u001b[0m\u001b[33m and\u001b[0m\u001b[33m the\u001b[0m\u001b[33m Minnesota\u001b[0m\u001b[33m Timber\u001b[0m\u001b[33mw\u001b[0m\u001b[33molves\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[30m\u001b[0m"
]
}
],
@@ -1595,7 +1670,7 @@
"agent_config = AgentConfig(\n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
- " tools=[search_tool],\n",
+ " tools=[\"brave_search\"],\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
@@ -1636,7 +1711,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"id": "GvVRuhO-GOov",
"metadata": {
"colab": {
@@ -1647,118 +1722,274 @@
"outputId": "cb988aa9-568b-4966-d500-575b7b24578f"
},
"outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "982386e16a5d4faf8f166b74c7524f15",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Batches: 0%| | 0/1 [00:00 ('Here is a csv, can you describe it ?', [Attachment(content='https://raw.githubusercontent.com/meta-llama/llama-stack-apps/main/examples/resources/inflation.csv', mime_type='test/csv')])\n"
+ "\u001b[32mUser> Can you describe the data in the context?\u001b[0m\n",
+ "\u001b[30m\u001b[0m"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "tools_for_turn: [AgentToolWithArgs(name='memory', args={'memory_bank_id': 'inflation_data_memory_bank'})]\n",
+ "tools_for_turn_set: {'memory'}\n",
+ "tool_name: memory\n",
+ "tool_def: identifier='memory' provider_resource_id='memory' provider_id='memory-runtime' type='tool' tool_group='memory_group' tool_host= description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments' parameters=[ToolParameter(name='input_messages', parameter_type='list', description='Input messages for which to retrieve memory', required=True, default=None)] built_in_type=None metadata={'config': {'memory_bank_configs': [{'bank_id': 'memory_bank_1d984362-ef6c-468e-b5eb-a12b0d782783', 'type': 'vector'}]}} tool_prompt_format=\n",
+ "tool_name: code_interpreter\n",
+ "tool_name: brave_search\n",
+ "tool_defs: {'memory': ToolDefinition(tool_name='memory', description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments', parameters={'input_messages': ToolParamDefinition(param_type='list', description='Input messages for which to retrieve memory', required=True, default=None)})}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7a73fec80df8444f875da4833dcf46f9",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Batches: 0%| | 0/1 [00:00 Tool:memory Args:{'query': '{\"role\":\"user\",\"content\":\"Can you describe the data in the context?\",\"context\":null}', 'memory_bank_id': 'inflation_data_memory_bank'}\u001b[0m\n",
+ "\u001b[36mtool_execution> fetched 3079 bytes from memory\u001b[0m\n",
+ "\u001b[33minference> \u001b[0m\u001b[33mThe\u001b[0m\u001b[33m data\u001b[0m\u001b[33m provided\u001b[0m\u001b[33m appears\u001b[0m\u001b[33m to\u001b[0m\u001b[33m be\u001b[0m\u001b[33m a\u001b[0m\u001b[33m list\u001b[0m\u001b[33m of\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m for\u001b[0m\u001b[33m a\u001b[0m\u001b[33m specific\u001b[0m\u001b[33m country\u001b[0m\u001b[33m or\u001b[0m\u001b[33m region\u001b[0m\u001b[33m,\u001b[0m\u001b[33m organized\u001b[0m\u001b[33m by\u001b[0m\u001b[33m year\u001b[0m\u001b[33m and\u001b[0m\u001b[33m month\u001b[0m\u001b[33m.\u001b[0m\u001b[33m The\u001b[0m\u001b[33m data\u001b[0m\u001b[33m spans\u001b[0m\u001b[33m from\u001b[0m\u001b[33m January\u001b[0m\u001b[33m \u001b[0m\u001b[33m201\u001b[0m\u001b[33m4\u001b[0m\u001b[33m to\u001b[0m\u001b[33m June\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m3\u001b[0m\u001b[33m.\n",
+ "\n",
+ "\u001b[0m\u001b[33mThe\u001b[0m\u001b[33m format\u001b[0m\u001b[33m is\u001b[0m\u001b[33m a\u001b[0m\u001b[33m comma\u001b[0m\u001b[33m-separated\u001b[0m\u001b[33m values\u001b[0m\u001b[33m (\u001b[0m\u001b[33mCSV\u001b[0m\u001b[33m)\u001b[0m\u001b[33m table\u001b[0m\u001b[33m with\u001b[0m\u001b[33m the\u001b[0m\u001b[33m following\u001b[0m\u001b[33m columns\u001b[0m\u001b[33m:\n",
+ "\n",
+ "\u001b[0m\u001b[33m1\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Year\u001b[0m\u001b[33m:\u001b[0m\u001b[33m The\u001b[0m\u001b[33m year\u001b[0m\u001b[33m for\u001b[0m\u001b[33m which\u001b[0m\u001b[33m the\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rate\u001b[0m\u001b[33m is\u001b[0m\u001b[33m recorded\u001b[0m\u001b[33m.\n",
+ "\u001b[0m\u001b[33m2\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Jan\u001b[0m\u001b[33m,\u001b[0m\u001b[33m Feb\u001b[0m\u001b[33m,\u001b[0m\u001b[33m Mar\u001b[0m\u001b[33m,\u001b[0m\u001b[33m ...,\u001b[0m\u001b[33m Dec\u001b[0m\u001b[33m:\u001b[0m\u001b[33m The\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rate\u001b[0m\u001b[33m for\u001b[0m\u001b[33m each\u001b[0m\u001b[33m month\u001b[0m\u001b[33m of\u001b[0m\u001b[33m the\u001b[0m\u001b[33m year\u001b[0m\u001b[33m,\u001b[0m\u001b[33m expressed\u001b[0m\u001b[33m as\u001b[0m\u001b[33m a\u001b[0m\u001b[33m decimal\u001b[0m\u001b[33m value\u001b[0m\u001b[33m.\n",
+ "\n",
+ "\u001b[0m\u001b[33mThe\u001b[0m\u001b[33m data\u001b[0m\u001b[33m suggests\u001b[0m\u001b[33m that\u001b[0m\u001b[33m the\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rate\u001b[0m\u001b[33m has\u001b[0m\u001b[33m fluct\u001b[0m\u001b[33muated\u001b[0m\u001b[33m over\u001b[0m\u001b[33m the\u001b[0m\u001b[33m years\u001b[0m\u001b[33m,\u001b[0m\u001b[33m with\u001b[0m\u001b[33m some\u001b[0m\u001b[33m periods\u001b[0m\u001b[33m of\u001b[0m\u001b[33m relatively\u001b[0m\u001b[33m low\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m (\u001b[0m\u001b[33me\u001b[0m\u001b[33m.g\u001b[0m\u001b[33m.,\u001b[0m\u001b[33m \u001b[0m\u001b[33m201\u001b[0m\u001b[33m4\u001b[0m\u001b[33m-\u001b[0m\u001b[33m201\u001b[0m\u001b[33m7\u001b[0m\u001b[33m)\u001b[0m\u001b[33m and\u001b[0m\u001b[33m some\u001b[0m\u001b[33m periods\u001b[0m\u001b[33m of\u001b[0m\u001b[33m higher\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m (\u001b[0m\u001b[33me\u001b[0m\u001b[33m.g\u001b[0m\u001b[33m.,\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m1\u001b[0m\u001b[33m-\u001b[0m\u001b[33m202\u001b[0m\u001b[33m2\u001b[0m\u001b[33m).\n",
+ "\n",
+ "\u001b[0m\u001b[33mSome\u001b[0m\u001b[33m observations\u001b[0m\u001b[33m from\u001b[0m\u001b[33m the\u001b[0m\u001b[33m data\u001b[0m\u001b[33m:\n",
+ "\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m In\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m were\u001b[0m\u001b[33m relatively\u001b[0m\u001b[33m stable\u001b[0m\u001b[33m from\u001b[0m\u001b[33m \u001b[0m\u001b[33m201\u001b[0m\u001b[33m4\u001b[0m\u001b[33m to\u001b[0m\u001b[33m \u001b[0m\u001b[33m201\u001b[0m\u001b[33m7\u001b[0m\u001b[33m,\u001b[0m\u001b[33m ranging\u001b[0m\u001b[33m from\u001b[0m\u001b[33m around\u001b[0m\u001b[33m \u001b[0m\u001b[33m1\u001b[0m\u001b[33m.\u001b[0m\u001b[33m6\u001b[0m\u001b[33m%\u001b[0m\u001b[33m to\u001b[0m\u001b[33m \u001b[0m\u001b[33m2\u001b[0m\u001b[33m.\u001b[0m\u001b[33m3\u001b[0m\u001b[33m%.\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m In\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m increased\u001b[0m\u001b[33m significantly\u001b[0m\u001b[33m in\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m1\u001b[0m\u001b[33m,\u001b[0m\u001b[33m with\u001b[0m\u001b[33m a\u001b[0m\u001b[33m peak\u001b[0m\u001b[33m of\u001b[0m\u001b[33m \u001b[0m\u001b[33m5\u001b[0m\u001b[33m.\u001b[0m\u001b[33m5\u001b[0m\u001b[33m%\u001b[0m\u001b[33m in\u001b[0m\u001b[33m December\u001b[0m\u001b[33m.\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m In\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m remained\u001b[0m\u001b[33m high\u001b[0m\u001b[33m in\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m2\u001b[0m\u001b[33m,\u001b[0m\u001b[33m with\u001b[0m\u001b[33m a\u001b[0m\u001b[33m peak\u001b[0m\u001b[33m of\u001b[0m\u001b[33m \u001b[0m\u001b[33m6\u001b[0m\u001b[33m.\u001b[0m\u001b[33m6\u001b[0m\u001b[33m%\u001b[0m\u001b[33m in\u001b[0m\u001b[33m August\u001b[0m\u001b[33m.\n",
+ "\u001b[0m\u001b[33m*\u001b[0m\u001b[33m In\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m have\u001b[0m\u001b[33m decreased\u001b[0m\u001b[33m slightly\u001b[0m\u001b[33m in\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m3\u001b[0m\u001b[33m,\u001b[0m\u001b[33m with\u001b[0m\u001b[33m a\u001b[0m\u001b[33m rate\u001b[0m\u001b[33m of\u001b[0m\u001b[33m \u001b[0m\u001b[33m4\u001b[0m\u001b[33m.\u001b[0m\u001b[33m8\u001b[0m\u001b[33m%\u001b[0m\u001b[33m in\u001b[0m\u001b[33m June\u001b[0m\u001b[33m.\n",
+ "\n",
+ "\u001b[0m\u001b[33mIt\u001b[0m\u001b[33m's\u001b[0m\u001b[33m worth\u001b[0m\u001b[33m noting\u001b[0m\u001b[33m that\u001b[0m\u001b[33m the\u001b[0m\u001b[33m data\u001b[0m\u001b[33m only\u001b[0m\u001b[33m includes\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m up\u001b[0m\u001b[33m to\u001b[0m\u001b[33m June\u001b[0m\u001b[33m \u001b[0m\u001b[33m202\u001b[0m\u001b[33m3\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m does\u001b[0m\u001b[33m not\u001b[0m\u001b[33m provide\u001b[0m\u001b[33m information\u001b[0m\u001b[33m on\u001b[0m\u001b[33m the\u001b[0m\u001b[33m underlying\u001b[0m\u001b[33m causes\u001b[0m\u001b[33m of\u001b[0m\u001b[33m the\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m or\u001b[0m\u001b[33m any\u001b[0m\u001b[33m potential\u001b[0m\u001b[33m factors\u001b[0m\u001b[33m that\u001b[0m\u001b[33m may\u001b[0m\u001b[33m influence\u001b[0m\u001b[33m future\u001b[0m\u001b[33m inflation\u001b[0m\u001b[33m rates\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[30m\u001b[0m\u001b[32mUser> Plot average yearly inflation as a time series\u001b[0m\n",
+ "\u001b[30m\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "INFO:httpx:HTTP Request: GET https://raw.githubusercontent.com/meta-llama/llama-stack-apps/main/examples/resources/inflation.csv \"HTTP/1.1 200 OK\"\n"
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "inference> import pandas as pd\n",
+ "tools_for_turn: [AgentToolWithArgs(name='memory', args={'memory_bank_id': 'inflation_data_memory_bank'}), 'code_interpreter']\n",
+ "tools_for_turn_set: {'memory', 'code_interpreter'}\n",
+ "tool_name: memory\n",
+ "tool_def: identifier='memory' provider_resource_id='memory' provider_id='memory-runtime' type='tool' tool_group='memory_group' tool_host= description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments' parameters=[ToolParameter(name='input_messages', parameter_type='list', description='Input messages for which to retrieve memory', required=True, default=None)] built_in_type=None metadata={'config': {'memory_bank_configs': [{'bank_id': 'memory_bank_1d984362-ef6c-468e-b5eb-a12b0d782783', 'type': 'vector'}]}} tool_prompt_format=\n",
+ "tool_name: code_interpreter\n",
+ "tool_def: identifier='code_interpreter' provider_resource_id='code_interpreter' provider_id='code-interpreter' type='tool' tool_group='code_interpreter_group' tool_host= description='' parameters=[] built_in_type= metadata={} tool_prompt_format=\n",
+ "tool_name: brave_search\n",
+ "tool_defs: {'memory': ToolDefinition(tool_name='memory', description='Memory tool to retrieve memory from a memory bank based on context of the input messages and attachments', parameters={'input_messages': ToolParamDefinition(param_type='list', description='Input messages for which to retrieve memory', required=True, default=None)}), : ToolDefinition(tool_name=, description=None, parameters=None)}\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:390: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_python(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n",
+ "/Users/dineshyv/miniconda3/envs/stack/lib/python3.10/site-packages/pydantic/main.py:441: UserWarning: Pydantic serializer warnings:\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " Failed to get discriminator value for tagged union serialization with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - defaulting to left to right union serialization.\n",
+ " PydanticSerializationUnexpectedValue: Expected `ImageContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " PydanticSerializationUnexpectedValue: Expected `TextContentItem` but got `list` with value `[TextContentItem(type='te...TRIEVED-CONTEXT ===\\n')]` - serialized value may not be as expected\n",
+ " return self.__pydantic_serializer__.to_json(\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b79a023a8ddd4f1d80c2c737affc3c91",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Batches: 0%| | 0/1 [00:00 Tool:memory Args:{'query': '{\"role\":\"user\",\"content\":\"Plot average yearly inflation as a time series\",\"context\":null}', 'memory_bank_id': 'inflation_data_memory_bank'}\u001b[0m\n",
+ "\u001b[36mtool_execution> fetched 3079 bytes from memory\u001b[0m\n",
+ "\u001b[33minference> \u001b[0m\u001b[36m\u001b[0m\u001b[36mimport\u001b[0m\u001b[36m pandas\u001b[0m\u001b[36m as\u001b[0m\u001b[36m pd\u001b[0m\u001b[36m\n",
"\n",
- "# Read the CSV file\n",
- "df = pd.read_csv('/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv')\n",
- "\n",
- "# Describe the CSV\n",
- "print(df.describe())\n",
- "tool_execution> Tool:code_interpreter Args:{'code': \"import pandas as pd\\n\\n# Read the CSV file\\ndf = pd.read_csv('/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv')\\n\\n# Describe the CSV\\nprint(df.describe())\"}\n",
- "tool_execution> Tool:code_interpreter Response:completed\n",
+ "\u001b[0m\u001b[36m#\u001b[0m\u001b[36m Define\u001b[0m\u001b[36m the\u001b[0m\u001b[36m data\u001b[0m\u001b[36m\n",
+ "\u001b[0m\u001b[36mdata\u001b[0m\u001b[36m =\u001b[0m\u001b[36m {\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mYear\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m201\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m201\u001b[0m\u001b[36m5\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m201\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m201\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m201\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m201\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m202\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m202\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m202\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m202\u001b[0m\u001b[36m3\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mJan\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mFeb\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m5\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mMar\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m5\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mApr\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m3\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m5\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mMay\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m3\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mJun\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m1\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m5\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mJul\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m6\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m5\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mAug\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m4\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m0\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m6\u001b[0m\u001b[36m.\u001b[0m\u001b[36m3\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m4\u001b[0m\u001b[36m.\u001b[0m\u001b[36m8\u001b[0m\u001b[36m],\n",
+ "\u001b[0m\u001b[36m \u001b[0m\u001b[36m \"\u001b[0m\u001b[36mSep\u001b[0m\u001b[36m\":\u001b[0m\u001b[36m [\u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m7\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[36m.\u001b[0m\u001b[36m9\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m2\u001b[0m\u001b[36m.\u001b[0m\u001b[36m2\u001b[0m\u001b[36m,\u001b[0m\u001b[36m \u001b[0m\u001b[36m1\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[32mtool_execution> Tool:code_interpreter Args:{'code': 'import pandas as pd\\n\\n# Define the data\\ndata = {\\n \"Year\": [2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023],\\n \"Jan\": [1.6, 1.6, 2.2, 2.3, 1.8, 2.2, 2.3, 1.4, 6.0, 5.6],\\n \"Feb\": [1.6, 1.7, 2.3, 2.2, 1.8, 2.1, 2.4, 1.3, 6.4, 5.5],\\n \"Mar\": [1.7, 1.8, 2.2, 2.0, 2.1, 2.0, 2.1, 1.6, 6.5, 5.6],\\n \"Apr\": [1.8, 1.8, 2.1, 1.9, 2.1, 2.1, 1.4, 3.0, 6.2, 5.5],\\n \"May\": [2.0, 1.7, 2.2, 1.7, 2.2, 2.0, 1.2, 3.8, 6.0, 5.3],\\n \"Jun\": [1.9, 1.8, 2.2, 1.7, 2.3, 2.1, 1.2, 4.5, 5.9, 4.8],\\n \"Jul\": [1.9, 1.8, 2.2, 1.7, 2.4, 2.2, 1.6, 4.3, 5.9, 4.8],\\n \"Aug\": [1.7, 1.8, 2.3, 1.7, 2.2, 2.4, 1.7, 4.0, 6.3, 4.8],\\n \"Sep\": [1.7, 1.9, 2.2, 1'}\u001b[0m\n",
+ "\u001b[32mtool_execution> Tool:code_interpreter Response:error\n",
"[stdout]\n",
- "Year Jan Feb Mar ... Sep Oct Nov Dec\n",
- "count 10.00000 10.000000 10.000000 10.000000 ... 10.000000 10.000000 10.000000 10.000000\n",
- "mean 2018.50000 2.700000 2.730000 2.760000 ... 2.850000 2.850000 2.850000 2.890000\n",
- "std 3.02765 1.667999 1.743591 1.757018 ... 1.593912 1.577093 1.551523 1.569466\n",
- "min 2014.00000 1.400000 1.300000 1.600000 ... 1.700000 1.600000 1.600000 1.600000\n",
- "25% 2016.25000 1.650000 1.725000 1.850000 ... 1.750000 1.825000 1.775000 1.875000\n",
- "50% 2018.50000 2.200000 2.150000 2.050000 ... 2.200000 2.100000 2.150000 2.200000\n",
- "75% 2020.75000 2.300000 2.375000 2.175000 ... 3.600000 3.575000 3.575000 3.500000\n",
- "max 2023.00000 6.000000 6.400000 6.500000 ... 6.600000 6.300000 6.000000 5.700000\n",
- "\n",
- "[8 rows x 13 columns]\n",
+ "[Errno 2] No such file or directory: 'bwrap'\n",
"[/stdout]\n",
- "shield_call> No Violation\n",
- "inference> The CSV file appears to be a dataset with 10 rows and 13 columns. The columns represent various economic indicators, such as inflation rates for each month from January to December, as well as year (yearly inflation rate).\n",
+ "[stderr]\n",
+ "[Errno 2] No such file or directory: 'bwrap'\n",
+ "[/stderr]\u001b[0m\n",
+ "\u001b[33minference> \u001b[0m"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+ "To disable this warning, you can either:\n",
+ "\t- Avoid using `tokenizers` before the fork if possible\n",
+ "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[33mThe\u001b[0m\u001b[33m error\u001b[0m\u001b[33m message\u001b[0m\u001b[33m indicates\u001b[0m\u001b[33m that\u001b[0m\u001b[33m the\u001b[0m\u001b[33m system\u001b[0m\u001b[33m cannot\u001b[0m\u001b[33m find\u001b[0m\u001b[33m the\u001b[0m\u001b[33m '\u001b[0m\u001b[33mb\u001b[0m\u001b[33mwrap\u001b[0m\u001b[33m'\u001b[0m\u001b[33m file\u001b[0m\u001b[33m,\u001b[0m\u001b[33m which\u001b[0m\u001b[33m is\u001b[0m\u001b[33m required\u001b[0m\u001b[33m for\u001b[0m\u001b[33m the\u001b[0m\u001b[33m plot\u001b[0m\u001b[33m to\u001b[0m\u001b[33m be\u001b[0m\u001b[33m displayed\u001b[0m\u001b[33m.\u001b[0m\u001b[33m This\u001b[0m\u001b[33m issue\u001b[0m\u001b[33m is\u001b[0m\u001b[33m likely\u001b[0m\u001b[33m due\u001b[0m\u001b[33m to\u001b[0m\u001b[33m a\u001b[0m\u001b[33m missing\u001b[0m\u001b[33m or\u001b[0m\u001b[33m incorrect\u001b[0m\u001b[33m installation\u001b[0m\u001b[33m of\u001b[0m\u001b[33m the\u001b[0m\u001b[33m '\u001b[0m\u001b[33mb\u001b[0m\u001b[33mwrap\u001b[0m\u001b[33m'\u001b[0m\u001b[33m package\u001b[0m\u001b[33m.\n",
"\n",
- "Here is a brief description of the data:\n",
+ "\u001b[0m\u001b[33mTo\u001b[0m\u001b[33m fix\u001b[0m\u001b[33m this\u001b[0m\u001b[33m issue\u001b[0m\u001b[33m,\u001b[0m\u001b[33m you\u001b[0m\u001b[33m can\u001b[0m\u001b[33m try\u001b[0m\u001b[33m reinstall\u001b[0m\u001b[33ming\u001b[0m\u001b[33m the\u001b[0m\u001b[33m '\u001b[0m\u001b[33mb\u001b[0m\u001b[33mwrap\u001b[0m\u001b[33m'\u001b[0m\u001b[33m package\u001b[0m\u001b[33m using\u001b[0m\u001b[33m pip\u001b[0m\u001b[33m:\n",
"\n",
- "* The `Year` column contains the year for which the inflation rate is reported.\n",
- "* The `Jan`, `Feb`, `Mar`, etc. columns contain the inflation rate for each month (January to December).\n",
- "* The `count` column is the count of non-null values in each column.\n",
- "* The `mean` column is the mean of the non-null values in each column.\n",
- "* The `std` column is the standard deviation of the non-null values in each column.\n",
- "* The `min` column is the minimum value in each column.\n",
- "* The `25%` column is the 25th percentile (25th percentile) of the non-null values in each column.\n",
- "* The `50%` column is the 50th percentile (50th percentile) of the non-null values in each column.\n",
- "* The `75%` column is the 75th percentile (75th percentile) of the non-null values in each column.\n",
- "* The `max` column is the maximum value in each column.\n",
+ "\u001b[0m\u001b[33mpip\u001b[0m\u001b[33m install\u001b[0m\u001b[33m b\u001b[0m\u001b[33mwrap\u001b[0m\u001b[33m\n",
"\n",
- "This dataset could be used for various applications, such as analyzing historical inflation rates, forecasting future inflation rates, or comparing inflation rates across different months or years.\n",
- "User> ('Which year ended with the highest inflation ?', None)\n",
- "inference> According to the data, the year with the highest inflation was 2023. The inflation rate for 2023 is 6.600%.\n",
- "User> ('What macro economic situations that led to such high inflation in that period?', None)\n",
- "inference> The high inflation rate in 2023 is likely attributed to a combination of macroeconomic factors, including:\n",
+ "\u001b[0m\u001b[33mIf\u001b[0m\u001b[33m the\u001b[0m\u001b[33m issue\u001b[0m\u001b[33m persists\u001b[0m\u001b[33m,\u001b[0m\u001b[33m you\u001b[0m\u001b[33m can\u001b[0m\u001b[33m try\u001b[0m\u001b[33m to\u001b[0m\u001b[33m display\u001b[0m\u001b[33m the\u001b[0m\u001b[33m plot\u001b[0m\u001b[33m using\u001b[0m\u001b[33m a\u001b[0m\u001b[33m different\u001b[0m\u001b[33m method\u001b[0m\u001b[33m,\u001b[0m\u001b[33m such\u001b[0m\u001b[33m as\u001b[0m\u001b[33m saving\u001b[0m\u001b[33m the\u001b[0m\u001b[33m plot\u001b[0m\u001b[33m to\u001b[0m\u001b[33m a\u001b[0m\u001b[33m file\u001b[0m\u001b[33m:\n",
"\n",
- "1. **Supply chain disruptions**: The COVID-19 pandemic and subsequent lockdowns led to supply chain disruptions, resulting in shortages and price increases for various goods and services.\n",
- "2. **Economic growth**: The rapid economic growth in the preceding years created demand for goods and services, leading to higher production costs and, subsequently, higher prices.\n",
- "3. **Monetary policy**: The central bank's easy-money policies, such as quantitative easing and low interest rates, increased the money supply and led to inflationary pressures.\n",
- "4. **Commodity price shocks**: Increases in global commodity prices, such as oil and food prices, contributed to higher production costs and inflation.\n",
- "5. **Labor market tightness**: The labor market has been tight, leading to higher wages and, subsequently, higher production costs, which have been passed on to consumers.\n",
- "6. **Trade wars and tariffs**: The ongoing trade tensions and tariffs imposed by various countries have disrupted global supply chains, leading to higher prices for imported goods.\n",
- "7. **Climate change and extreme weather events**: The increasing frequency and severity of extreme weather events, such as heatwaves and droughts, have disrupted agricultural production and supply chains.\n",
- "8. **Currency devaluation**: A devaluation of the currency can make imports more expensive, leading to higher inflation.\n",
- "9. **Government spending and fiscal policy**: Government spending and fiscal policy decisions, such as tax cuts and increased government spending, can inject more money into the economy, leading to inflation.\n",
- "10. **Monetary policy mistakes**: Mistakes in monetary policy, such as premature interest rate hikes or overly aggressive quantitative easing, can lead to inflationary pressures.\n",
+ "\u001b[0m\u001b[33mimport\u001b[0m\u001b[33m matplotlib\u001b[0m\u001b[33m.pyplot\u001b[0m\u001b[33m as\u001b[0m\u001b[33m plt\u001b[0m\u001b[33m\n",
"\n",
- "It's worth noting that the specific factors contributing to the high inflation rate in 2023 may vary depending on the region, country, or even specific economy.\n",
- "User> ('Plot average yearly inflation as a time series', None)\n",
- "inference> import pandas as pd\n",
- "import matplotlib.pyplot as plt\n",
+ "\u001b[0m\u001b[33m#\u001b[0m\u001b[33m ...\u001b[0m\u001b[33m (\u001b[0m\u001b[33mrest\u001b[0m\u001b[33m of\u001b[0m\u001b[33m the\u001b[0m\u001b[33m code\u001b[0m\u001b[33m remains\u001b[0m\u001b[33m the\u001b[0m\u001b[33m same\u001b[0m\u001b[33m)\n",
"\n",
- "# Read the CSV file\n",
- "df = pd.read_csv('/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv')\n",
+ "\u001b[0m\u001b[33mplt\u001b[0m\u001b[33m.savefig\u001b[0m\u001b[33m('\u001b[0m\u001b[33min\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m_rate\u001b[0m\u001b[33m.png\u001b[0m\u001b[33m')\n",
"\n",
- "# Extract the year and inflation rate from the CSV file\n",
- "df['Year'] = pd.to_datetime(df['Year'], format='%Y')\n",
- "df = df.rename(columns={'Jan': 'Jan Rate', 'Feb': 'Feb Rate', 'Mar': 'Mar Rate', 'Apr': 'Apr Rate', 'May': 'May Rate', 'Jun': 'Jun Rate', 'Jul': 'Jul Rate', 'Aug': 'Aug Rate', 'Sep': 'Sep Rate', 'Oct': 'Oct Rate', 'Nov': 'Nov Rate', 'Dec': 'Dec Rate'})\n",
- "\n",
- "# Calculate the average yearly inflation rate\n",
- "df['Yearly Inflation'] = df[['Jan Rate', 'Feb Rate', 'Mar Rate', 'Apr Rate', 'May Rate', 'Jun Rate', 'Jul Rate', 'Aug Rate', 'Sep Rate', 'Oct Rate', 'Nov Rate', 'Dec Rate']].mean(axis=1)\n",
- "\n",
- "# Plot the average yearly inflation rate as a time series\n",
- "plt.figure(figsize=(10, 6))\n",
- "plt.plot(df['Year'], df['Yearly Inflation'], marker='o')\n",
- "plt.title('Average Yearly Inflation Rate')\n",
- "plt.xlabel('Year')\n",
- "plt.ylabel('Inflation Rate (%)')\n",
- "plt.grid(True)\n",
- "plt.show()\n",
- "tool_execution> Tool:code_interpreter Args:{'code': \"import pandas as pd\\nimport matplotlib.pyplot as plt\\n\\n# Read the CSV file\\ndf = pd.read_csv('/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv')\\n\\n# Extract the year and inflation rate from the CSV file\\ndf['Year'] = pd.to_datetime(df['Year'], format='%Y')\\ndf = df.rename(columns={'Jan': 'Jan Rate', 'Feb': 'Feb Rate', 'Mar': 'Mar Rate', 'Apr': 'Apr Rate', 'May': 'May Rate', 'Jun': 'Jun Rate', 'Jul': 'Jul Rate', 'Aug': 'Aug Rate', 'Sep': 'Sep Rate', 'Oct': 'Oct Rate', 'Nov': 'Nov Rate', 'Dec': 'Dec Rate'})\\n\\n# Calculate the average yearly inflation rate\\ndf['Yearly Inflation'] = df[['Jan Rate', 'Feb Rate', 'Mar Rate', 'Apr Rate', 'May Rate', 'Jun Rate', 'Jul Rate', 'Aug Rate', 'Sep Rate', 'Oct Rate', 'Nov Rate', 'Dec Rate']].mean(axis=1)\\n\\n# Plot the average yearly inflation rate as a time series\\nplt.figure(figsize=(10, 6))\\nplt.plot(df['Year'], df['Yearly Inflation'], marker='o')\\nplt.title('Average Yearly Inflation Rate')\\nplt.xlabel('Year')\\nplt.ylabel('Inflation Rate (%)')\\nplt.grid(True)\\nplt.show()\"}\n",
- "tool_execution> Tool:code_interpreter Response:completed\n",
- "shield_call> No Violation\n",
- "inference> This code reads the CSV file, extracts the year and inflation rate, calculates the average yearly inflation rate, and plots the average yearly inflation rate as a time series. The resulting plot shows the average inflation rate over the years.\n"
+ "\u001b[0m\u001b[33mThis\u001b[0m\u001b[33m will\u001b[0m\u001b[33m save\u001b[0m\u001b[33m the\u001b[0m\u001b[33m plot\u001b[0m\u001b[33m to\u001b[0m\u001b[33m a\u001b[0m\u001b[33m file\u001b[0m\u001b[33m named\u001b[0m\u001b[33m '\u001b[0m\u001b[33min\u001b[0m\u001b[33mflation\u001b[0m\u001b[33m_rate\u001b[0m\u001b[33m.png\u001b[0m\u001b[33m'\u001b[0m\u001b[33m in\u001b[0m\u001b[33m the\u001b[0m\u001b[33m current\u001b[0m\u001b[33m working\u001b[0m\u001b[33m directory\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
+ "\u001b[30m\u001b[0m"
]
}
],
"source": [
"agent_config = AgentConfig(\n",
+ " sampling_params = {\n",
+ " \"max_tokens\" : 4096,\n",
+ " \"temperature\": 0.0\n",
+ " },\n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" tools=[\n",
- " search_tool,\n",
- " {\n",
- " \"type\": \"code_interpreter\",\n",
- " }\n",
+ " \"brave_search\",\n",
+ " \"code_interpreter\",\n",
" ],\n",
" tool_choice=\"required\",\n",
" input_shields=[],\n",
@@ -1766,38 +1997,48 @@
" enable_session_persistence=False,\n",
")\n",
"\n",
+ "memory_bank_id = \"inflation_data_memory_bank\"\n",
+ "client.memory_banks.register(\n",
+ " memory_bank_id=memory_bank_id,\n",
+ " params={\n",
+ " \"memory_bank_type\": \"vector\",\n",
+ " \"embedding_model\": \"all-MiniLM-L6-v2\",\n",
+ " \"chunk_size_in_tokens\": 512,\n",
+ " \"overlap_size_in_tokens\": 64,\n",
+ " },\n",
+ ")\n",
+ "AugmentConfigWithMemoryTool(agent_config, client)\n",
"codex_agent = Agent(client, agent_config)\n",
"session_id = codex_agent.create_session(\"test-session\")\n",
"\n",
+ "client.memory.insert(\n",
+ " bank_id=memory_bank_id,\n",
+ " documents=[\n",
+ " Document(\n",
+ " document_id=\"inflation\",\n",
+ " content=\"https://raw.githubusercontent.com/meta-llama/llama-stack-apps/main/examples/resources/inflation.csv\",\n",
+ " mime_type=\"text/csv\",\n",
+ " metadata={},\n",
+ " )\n",
+ " ],\n",
+ ")\n",
+ "\n",
"user_prompts = [\n",
- " (\n",
- " \"Here is a csv, can you describe it ?\",\n",
- " [\n",
- " Attachment(\n",
- " content=\"https://raw.githubusercontent.com/meta-llama/llama-stack-apps/main/examples/resources/inflation.csv\",\n",
- " mime_type=\"test/csv\",\n",
- " )\n",
- " ],\n",
- " ),\n",
- " (\"Which year ended with the highest inflation ?\", None),\n",
- " (\n",
- " \"What macro economic situations that led to such high inflation in that period?\",\n",
- " None,\n",
- " ),\n",
- " (\"Plot average yearly inflation as a time series\", None),\n",
+ " {\"prompt\": \"Can you describe the data in the context?\", \"tools\": [{\"name\": \"memory\", \"args\": {\"memory_bank_id\": memory_bank_id}}]},\n",
+ " {\"prompt\": \"Plot average yearly inflation as a time series\", \"tools\": [{\"name\": \"memory\", \"args\": {\"memory_bank_id\": memory_bank_id}}, \"code_interpreter\"]},\n",
"]\n",
"\n",
- "for prompt in user_prompts:\n",
- " cprint(f'User> {prompt}', 'green')\n",
+ "for input in user_prompts:\n",
+ " cprint(f'User> {input[\"prompt\"]}', 'green')\n",
" response = codex_agent.create_turn(\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",
- " \"content\": prompt[0],\n",
+ " \"content\": input[\"prompt\"],\n",
" }\n",
" ],\n",
- " attachments=prompt[1],\n",
" session_id=session_id,\n",
+ " tools=input[\"tools\"],\n",
" )\n",
" # for chunk in response:\n",
" # print(chunk)\n",
@@ -1818,7 +2059,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"id": "JqBBVLKdIHHq",
"metadata": {
"colab": {
@@ -1830,14 +2071,20 @@
},
"outputs": [
{
- "data": {
- "image/png": "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",
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "output_type": "display_data"
+ "ename": "FileNotFoundError",
+ "evalue": "[Errno 2] No such file or directory: '/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[5], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpyplot\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mplt\u001b[39;00m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;66;03m# Read the CSV file\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;66;03m# Extract the year and inflation rate from the CSV file\u001b[39;00m\n\u001b[1;32m 8\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mYear\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_datetime(df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mYear\u001b[39m\u001b[38;5;124m'\u001b[39m], \u001b[38;5;28mformat\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mY\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
+ "File \u001b[0;32m~/miniconda3/envs/stack/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 1014\u001b[0m dialect,\n\u001b[1;32m 1015\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1022\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 1023\u001b[0m )\n\u001b[1;32m 1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/miniconda3/envs/stack/lib/python3.10/site-packages/pandas/io/parsers/readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m 619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m 623\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
+ "File \u001b[0;32m~/miniconda3/envs/stack/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1617\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/miniconda3/envs/stack/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1878\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[1;32m 1879\u001b[0m mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1881\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1882\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1883\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1884\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1885\u001b[0m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1886\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1887\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1888\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1889\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
+ "File \u001b[0;32m~/miniconda3/envs/stack/lib/python3.10/site-packages/pandas/io/common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 869\u001b[0m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[1;32m 870\u001b[0m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[1;32m 871\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[1;32m 872\u001b[0m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[0;32m--> 873\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 874\u001b[0m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 875\u001b[0m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 876\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 877\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 878\u001b[0m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 879\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 880\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 881\u001b[0m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[1;32m 882\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
+ "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '/tmp/tmpco0s0o4_/LOdZoVp1inflation.csv'"
+ ]
}
],
"source": [
diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html
index 33ca52363..5a78f5bae 100644
--- a/docs/resources/llama-stack-spec.html
+++ b/docs/resources/llama-stack-spec.html
@@ -3974,6 +3974,41 @@
"stream": {
"type": "boolean"
},
+ "documents": {
+ "type": "array",
+ "items": {
+ "type": "object",
+ "properties": {
+ "content": {
+ "oneOf": [
+ {
+ "type": "string"
+ },
+ {
+ "$ref": "#/components/schemas/InterleavedContentItem"
+ },
+ {
+ "type": "array",
+ "items": {
+ "$ref": "#/components/schemas/InterleavedContentItem"
+ }
+ },
+ {
+ "$ref": "#/components/schemas/URL"
+ }
+ ]
+ },
+ "mime_type": {
+ "type": "string"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "content",
+ "mime_type"
+ ]
+ }
+ },
"tools": {
"type": "array",
"items": {
diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml
index 4da311cf0..72093b436 100644
--- a/docs/resources/llama-stack-spec.yaml
+++ b/docs/resources/llama-stack-spec.yaml
@@ -618,6 +618,25 @@ components:
properties:
agent_id:
type: string
+ documents:
+ items:
+ additionalProperties: false
+ properties:
+ content:
+ oneOf:
+ - type: string
+ - $ref: '#/components/schemas/InterleavedContentItem'
+ - items:
+ $ref: '#/components/schemas/InterleavedContentItem'
+ type: array
+ - $ref: '#/components/schemas/URL'
+ mime_type:
+ type: string
+ required:
+ - content
+ - mime_type
+ type: object
+ type: array
messages:
items:
oneOf:
diff --git a/llama_stack/apis/agents/agents.py b/llama_stack/apis/agents/agents.py
index 18bbcd95c..acf8fa748 100644
--- a/llama_stack/apis/agents/agents.py
+++ b/llama_stack/apis/agents/agents.py
@@ -45,6 +45,11 @@ class Attachment(BaseModel):
mime_type: str
+class Document(BaseModel):
+ content: InterleavedContent | URL
+ mime_type: str
+
+
class StepCommon(BaseModel):
turn_id: str
step_id: str
@@ -272,6 +277,9 @@ class AgentTurnCreateRequest(AgentConfigOverridablePerTurn):
]
]
+ documents: Optional[List[Document]] = None
+ tools: Optional[List[AgentTool]] = None
+
stream: Optional[bool] = False
@@ -308,6 +316,7 @@ class Agents(Protocol):
]
],
stream: Optional[bool] = False,
+ documents: Optional[List[Document]] = None,
tools: Optional[List[AgentTool]] = None,
) -> Union[Turn, AsyncIterator[AgentTurnResponseStreamChunk]]: ...
diff --git a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
index 2af1c820b..43d5cbdb7 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
@@ -33,13 +33,18 @@ from llama_stack.apis.agents import (
AgentTurnResponseTurnCompletePayload,
AgentTurnResponseTurnStartPayload,
Attachment,
+ Document,
InferenceStep,
ShieldCallStep,
StepType,
ToolExecutionStep,
Turn,
)
-from llama_stack.apis.common.content_types import TextContentItem, URL
+from llama_stack.apis.common.content_types import (
+ InterleavedContent,
+ TextContentItem,
+ URL,
+)
from llama_stack.apis.inference import (
ChatCompletionResponseEventType,
CompletionMessage,
@@ -55,8 +60,8 @@ from llama_stack.apis.inference import (
ToolResponseMessage,
UserMessage,
)
-from llama_stack.apis.memory import Memory
-from llama_stack.apis.memory_banks import MemoryBanks
+from llama_stack.apis.memory import Memory, MemoryBankDocument
+from llama_stack.apis.memory_banks import MemoryBanks, VectorMemoryBankParams
from llama_stack.apis.safety import Safety
from llama_stack.apis.tools import ToolGroups, ToolRuntime
from llama_stack.providers.utils.kvstore import KVStore
@@ -190,6 +195,7 @@ class ChatAgent(ShieldRunnerMixin):
input_messages=messages,
sampling_params=self.agent_config.sampling_params,
stream=request.stream,
+ documents=request.documents,
tools_for_turn=request.tools,
):
if isinstance(chunk, CompletionMessage):
@@ -240,6 +246,7 @@ class ChatAgent(ShieldRunnerMixin):
input_messages: List[Message],
sampling_params: SamplingParams,
stream: bool = False,
+ documents: Optional[List[Document]] = None,
tools_for_turn: Optional[List[AgentTool]] = None,
) -> AsyncGenerator:
# Doing async generators makes downstream code much simpler and everything amenable to
@@ -257,7 +264,13 @@ class ChatAgent(ShieldRunnerMixin):
yield res
async for res in self._run(
- session_id, turn_id, input_messages, sampling_params, stream, tools_for_turn
+ session_id,
+ turn_id,
+ input_messages,
+ sampling_params,
+ stream,
+ documents,
+ tools_for_turn,
):
if isinstance(res, bool):
return
@@ -352,6 +365,7 @@ class ChatAgent(ShieldRunnerMixin):
input_messages: List[Message],
sampling_params: SamplingParams,
stream: bool = False,
+ documents: Optional[List[Document]] = None,
tools_for_turn: Optional[List[AgentTool]] = None,
) -> AsyncGenerator:
tool_args = {}
@@ -361,6 +375,7 @@ class ChatAgent(ShieldRunnerMixin):
tool_args[tool.name] = tool.args
tool_defs = await self._get_tool_defs(tools_for_turn)
+ await self.handle_documents(session_id, documents, input_messages, tool_defs)
if "memory" in tool_defs and len(input_messages) > 0:
with tracing.span("memory_tool") as span:
step_id = str(uuid.uuid4())
@@ -378,6 +393,11 @@ class ChatAgent(ShieldRunnerMixin):
"query": input_messages[-1],
**extra_args,
}
+
+ session_info = await self.storage.get_session_info(session_id)
+ # if the session has a memory bank id, let the memory tool use it
+ if session_info.memory_bank_id:
+ args["memory_bank_id"] = session_info.memory_bank_id
serialized_args = tracing.serialize_value(args)
yield AgentTurnResponseStreamChunk(
event=AgentTurnResponseEvent(
@@ -732,6 +752,112 @@ class ChatAgent(ShieldRunnerMixin):
return ret
+ async def handle_documents(
+ self,
+ session_id: str,
+ documents: List[Document],
+ input_messages: List[Message],
+ tool_defs: Dict[str, ToolDefinition],
+ ) -> None:
+ memory_tool = tool_defs.get("memory", None)
+ code_interpreter_tool = tool_defs.get("code_interpreter", None)
+ if documents:
+ content_items = [
+ d for d in documents if isinstance(d.content, InterleavedContent)
+ ]
+ url_items = [d for d in documents if isinstance(d.content, URL)]
+ pattern = re.compile("^(https?://|file://|data:)")
+ url_items = [
+ URL(uri=a.content) for a in url_items if pattern.match(a.content)
+ ]
+ # Save the contents to a tempdir and use its path as a URL if code interpreter is present
+ if code_interpreter_tool:
+ for c in content_items:
+ temp_file_path = os.path.join(
+ self.tempdir, f"{make_random_string()}.txt"
+ )
+ with open(temp_file_path, "w") as temp_file:
+ temp_file.write(c.content)
+ url_items.append(URL(uri=f"file://{temp_file_path}"))
+
+ if memory_tool and code_interpreter_tool:
+ # if both memory and code_interpreter are available, we download the URLs
+ # and attach the data to the last message.
+ msg = await attachment_message(self.tempdir, url_items)
+ input_messages.append(msg)
+ # Since memory is present, add all the data to the memory bank
+ await self.add_to_session_memory_bank(session_id, documents)
+ elif code_interpreter_tool:
+ # if only code_interpreter is available, we download the URLs to a tempdir
+ # and attach the path to them as a message to inference with the
+ # assumption that the model invokes the code_interpreter tool with the path
+ msg = await attachment_message(self.tempdir, url_items)
+ input_messages.append(msg)
+ elif memory_tool:
+ # if only memory is available, we load the data from the URLs and content items to the memory bank
+ await self.add_to_session_memory_bank(session_id, documents)
+ else:
+ # if no memory or code_interpreter tool is available,
+ # we try to load the data from the URLs and content items as a message to inference
+ # and add it to the last message's context
+ input_messages[-1].context = content_items + load_data_from_urls(
+ url_items
+ )
+
+ async def _ensure_memory_bank(self, session_id: str) -> str:
+ session_info = await self.storage.get_session_info(session_id)
+ if session_info is None:
+ raise ValueError(f"Session {session_id} not found")
+
+ if session_info.memory_bank_id is None:
+ bank_id = f"memory_bank_{session_id}"
+ await self.memory_banks_api.register_memory_bank(
+ memory_bank_id=bank_id,
+ params=VectorMemoryBankParams(
+ embedding_model="all-MiniLM-L6-v2",
+ chunk_size_in_tokens=512,
+ ),
+ )
+ await self.storage.add_memory_bank_to_session(session_id, bank_id)
+ else:
+ bank_id = session_info.memory_bank_id
+
+ return bank_id
+
+ async def add_to_session_memory_bank(
+ self, session_id: str, data: List[Document]
+ ) -> None:
+ bank_id = await self._ensure_memory_bank(session_id)
+ documents = [
+ MemoryBankDocument(
+ document_id=str(uuid.uuid4()),
+ content=a.content,
+ mime_type=a.mime_type,
+ metadata={},
+ )
+ for a in data
+ ]
+ await self.memory_api.insert_documents(
+ bank_id=bank_id,
+ documents=documents,
+ )
+
+
+async def load_data_from_urls(urls: List[URL]) -> List[str]:
+ data = []
+ for url in urls:
+ uri = url.uri
+ if uri.startswith("file://"):
+ filepath = uri[len("file://") :]
+ with open(filepath, "r") as f:
+ data.append(f.read())
+ elif uri.startswith("http"):
+ async with httpx.AsyncClient() as client:
+ r = await client.get(uri)
+ resp = r.text
+ data.append(resp)
+ return data
+
async def attachment_message(tempdir: str, urls: List[URL]) -> ToolResponseMessage:
content = []
diff --git a/llama_stack/providers/inline/agents/meta_reference/agents.py b/llama_stack/providers/inline/agents/meta_reference/agents.py
index ab7f8878f..0181ef609 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agents.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agents.py
@@ -21,6 +21,7 @@ from llama_stack.apis.agents import (
AgentStepResponse,
AgentTool,
AgentTurnCreateRequest,
+ Document,
Session,
Turn,
)
@@ -147,6 +148,7 @@ class MetaReferenceAgentsImpl(Agents):
]
],
tools: Optional[List[AgentTool]] = None,
+ documents: Optional[List[Document]] = None,
stream: Optional[bool] = False,
) -> AsyncGenerator:
request = AgentTurnCreateRequest(
@@ -155,6 +157,7 @@ class MetaReferenceAgentsImpl(Agents):
messages=messages,
stream=True,
tools=tools,
+ documents=documents,
)
if stream:
return self._create_agent_turn_streaming(request)
diff --git a/llama_stack/providers/inline/agents/meta_reference/persistence.py b/llama_stack/providers/inline/agents/meta_reference/persistence.py
index 144f65863..58b69858b 100644
--- a/llama_stack/providers/inline/agents/meta_reference/persistence.py
+++ b/llama_stack/providers/inline/agents/meta_reference/persistence.py
@@ -21,6 +21,7 @@ log = logging.getLogger(__name__)
class AgentSessionInfo(BaseModel):
session_id: str
session_name: str
+ memory_bank_id: Optional[str] = None
started_at: datetime
@@ -51,6 +52,17 @@ class AgentPersistence:
return AgentSessionInfo(**json.loads(value))
+ async def add_memory_bank_to_session(self, session_id: str, bank_id: str):
+ session_info = await self.get_session_info(session_id)
+ if session_info is None:
+ raise ValueError(f"Session {session_id} not found")
+
+ session_info.memory_bank_id = bank_id
+ await self.kvstore.set(
+ key=f"session:{self.agent_id}:{session_id}",
+ value=session_info.model_dump_json(),
+ )
+
async def add_turn_to_session(self, session_id: str, turn: Turn):
await self.kvstore.set(
key=f"session:{self.agent_id}:{session_id}:{turn.turn_id}",
diff --git a/llama_stack/providers/tests/agents/test_agents.py b/llama_stack/providers/tests/agents/test_agents.py
index cb20e5890..18dc90420 100644
--- a/llama_stack/providers/tests/agents/test_agents.py
+++ b/llama_stack/providers/tests/agents/test_agents.py
@@ -15,6 +15,7 @@ from llama_stack.apis.agents import (
AgentTurnResponseStepCompletePayload,
AgentTurnResponseStreamChunk,
AgentTurnResponseTurnCompletePayload,
+ Document,
ShieldCallStep,
StepType,
ToolChoice,
@@ -22,8 +23,6 @@ from llama_stack.apis.agents import (
Turn,
)
from llama_stack.apis.inference import CompletionMessage, SamplingParams, UserMessage
-from llama_stack.apis.memory import MemoryBankDocument
-from llama_stack.apis.memory_banks import VectorMemoryBankParams
from llama_stack.apis.safety import ViolationLevel
from llama_stack.providers.datatypes import Api
@@ -232,8 +231,6 @@ class TestAgents:
common_params,
):
agents_impl = agents_stack.impls[Api.agents]
- memory_banks_impl = agents_stack.impls[Api.memory_banks]
- memory_impl = agents_stack.impls[Api.memory]
urls = [
"memory_optimizations.rst",
"chat.rst",
@@ -243,28 +240,12 @@ class TestAgents:
"lora_finetune.rst",
]
documents = [
- MemoryBankDocument(
- document_id=f"num-{i}",
+ Document(
content=f"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}",
mime_type="text/plain",
- metadata={},
)
for i, url in enumerate(urls)
]
- await memory_banks_impl.register_memory_bank(
- memory_bank_id="test_bank",
- params=VectorMemoryBankParams(
- embedding_model="all-MiniLM-L6-v2",
- chunk_size_in_tokens=512,
- overlap_size_in_tokens=64,
- ),
- provider_id="faiss",
- )
- memory_impl.insert_documents(
- bank_id="test_bank",
- documents=documents,
- )
-
agent_config = AgentConfig(
**{
**common_params,
@@ -278,6 +259,7 @@ class TestAgents:
agent_id=agent_id,
session_id=session_id,
messages=attachment_message,
+ documents=documents,
stream=True,
)
turn_response = [
diff --git a/tests/client-sdk/agents/test_agents.py b/tests/client-sdk/agents/test_agents.py
index 64c3c159f..a77bb6cab 100644
--- a/tests/client-sdk/agents/test_agents.py
+++ b/tests/client-sdk/agents/test_agents.py
@@ -203,6 +203,79 @@ def test_builtin_tool_code_execution(llama_stack_client, agent_config):
assert "Tool:code_interpreter Response" in logs_str
+def test_code_execution(llama_stack_client):
+ agent_config = AgentConfig(
+ model="meta-llama/Llama-3.1-70B-Instruct",
+ instructions="You are a helpful assistant",
+ tools=[
+ "brave_search",
+ "code_interpreter",
+ ],
+ tool_choice="required",
+ input_shields=[],
+ output_shields=[],
+ enable_session_persistence=False,
+ )
+
+ memory_bank_id = "inflation_data_memory_bank"
+ llama_stack_client.memory_banks.register(
+ memory_bank_id=memory_bank_id,
+ params={
+ "memory_bank_type": "vector",
+ "embedding_model": "all-MiniLM-L6-v2",
+ "chunk_size_in_tokens": 512,
+ "overlap_size_in_tokens": 64,
+ },
+ )
+ AugmentConfigWithMemoryTool(agent_config, llama_stack_client)
+ codex_agent = Agent(llama_stack_client, agent_config)
+ session_id = codex_agent.create_session("test-session")
+
+ llama_stack_client.memory.insert(
+ bank_id=memory_bank_id,
+ documents=[
+ Document(
+ document_id="inflation",
+ content="https://raw.githubusercontent.com/meta-llama/llama-stack-apps/main/examples/resources/inflation.csv",
+ mime_type="text/csv",
+ metadata={},
+ )
+ ],
+ )
+
+ user_prompts = [
+ {
+ "prompt": "Can you describe the data in the context?",
+ "tools": [{"name": "memory", "args": {"memory_bank_id": memory_bank_id}}],
+ },
+ {
+ "prompt": "Plot average yearly inflation as a time series",
+ "tools": [
+ {"name": "memory", "args": {"memory_bank_id": memory_bank_id}},
+ "code_interpreter",
+ ],
+ },
+ ]
+
+ for input in user_prompts:
+ print(f'User> {input["prompt"]}')
+ response = codex_agent.create_turn(
+ messages=[
+ {
+ "role": "user",
+ "content": input["prompt"],
+ }
+ ],
+ session_id=session_id,
+ tools=input["tools"],
+ )
+ # for chunk in response:
+ # print(chunk)
+
+ for log in EventLogger().log(response):
+ log.print()
+
+
def test_custom_tool(llama_stack_client, agent_config):
client_tool = TestClientTool()
agent_config = {