github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-02 19:47:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

langchain[minor]: Generic configurable model (#23419)

Browse Source 
alternative to
[23244](https://github.com/langchain-ai/langchain/pull/23244). allows
you to use chat model declarative methods

![Screenshot 2024-06-25 at 1 07 10
PM](https://github.com/langchain-ai/langchain/assets/22008038/910d1694-9b7b-46bc-bc2e-3792df9321d6)
This commit is contained in:
Bagatur
2024-07-14 18:11:01 -07:00
committed by GitHub
parent d0728b0ba0
commit 0da5078cad
9 changed files with 1067 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

243
docs/docs/how_to/chat_models_universal_init.ipynb
View File

@@ -25,7 +25,7 @@
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain langchain-openai langchain-anthropic langchain-google-vertexai"
"%pip install -qU langchain>=0.2.7 langchain-openai langchain-anthropic langchain-google-vertexai"
]
},
{
@@ -76,32 +76,6 @@
"print(\"Gemini 1.5: \" + gemini_15.invoke(\"what's your name\").content + \"\\n\")"
]
},
{
"cell_type": "markdown",
"id": "fff9a4c8-b6ee-4a1a-8d3d-0ecaa312d4ed",
"metadata": {},
"source": [
"## Simple config example"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "75c25d39-bf47-4b51-a6c6-64d9c572bfd6",
"metadata": {},
"outputs": [],
"source": [
"user_config = {\n",
" \"model\": \"...user-specified...\",\n",
" \"model_provider\": \"...user-specified...\",\n",
" \"temperature\": 0,\n",
" \"max_tokens\": 1000,\n",
"}\n",
"\n",
"llm = init_chat_model(**user_config)\n",
"llm.invoke(\"what's your name\")"
]
},
{
"cell_type": "markdown",
"id": "f811f219-5e78-4b62-b495-915d52a22532",
@@ -125,12 +99,215 @@
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "da07b5c0-d2e6-42e4-bfcd-2efcfaae6221",
"cell_type": "markdown",
"id": "476a44db-c50d-4846-951d-0f1c9ba8bbaa",
"metadata": {},
"outputs": [],
"source": []
"source": [
"## Creating a configurable model\n",
"\n",
"You can also create a runtime-configurable model by specifying `configurable_fields`. If you don't specify a `model` value, then \"model\" and \"model_provider\" be configurable by default."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "6c037f27-12d7-4e83-811e-4245c0e3ba58",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90', 'finish_reason': 'stop', 'logprobs': None}, id='run-5428ab5c-b5c0-46de-9946-5d4ca40dbdc8-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"configurable_model = init_chat_model(temperature=0)\n",
"\n",
"configurable_model.invoke(\n",
" \"what's your name\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "321e3036-abd2-4e1f-bcc6-606efd036954",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_012XvotUJ3kGLXJUWKBVxJUi', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-1ad1eefe-f1c6-4244-8bc6-90e2cb7ee554-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"configurable_model.invoke(\n",
" \"what's your name\", config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}}\n",
")"
]
},
{
"cell_type": "markdown",
"id": "7f3b3d4a-4066-45e4-8297-ea81ac8e70b7",
"metadata": {},
"source": [
"### Configurable model with default values\n",
"\n",
"We can create a configurable model with default model values, specify which parameters are configurable, and add prefixes to configurable params:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "814a2289-d0db-401e-b555-d5116112b413",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"I'm an AI language model created by OpenAI, and I don't have a personal name. You can call me Assistant or any other name you prefer! How can I assist you today?\", response_metadata={'token_usage': {'completion_tokens': 37, 'prompt_tokens': 11, 'total_tokens': 48}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f', 'finish_reason': 'stop', 'logprobs': None}, id='run-3923e328-7715-4cd6-b215-98e4b6bf7c9d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 37, 'total_tokens': 48})"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"first_llm = init_chat_model(\n",
" model=\"gpt-4o\",\n",
" temperature=0,\n",
" configurable_fields=(\"model\", \"model_provider\", \"temperature\", \"max_tokens\"),\n",
" config_prefix=\"first\", # useful when you have a chain with multiple models\n",
")\n",
"\n",
"first_llm.invoke(\"what's your name\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "6c8755ba-c001-4f5a-a497-be3f1db83244",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"My name is Claude. It's nice to meet you!\", response_metadata={'id': 'msg_01RyYR64DoMPNCfHeNnroMXm', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 11, 'output_tokens': 15}}, id='run-22446159-3723-43e6-88df-b84797e7751d-0', usage_metadata={'input_tokens': 11, 'output_tokens': 15, 'total_tokens': 26})"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"first_llm.invoke(\n",
" \"what's your name\",\n",
" config={\n",
" \"configurable\": {\n",
" \"first_model\": \"claude-3-5-sonnet-20240620\",\n",
" \"first_temperature\": 0.5,\n",
" \"first_max_tokens\": 100,\n",
" }\n",
" },\n",
")"
]
},
{
"cell_type": "markdown",
"id": "0072b1a3-7e44-4b4e-8b07-efe1ba91a689",
"metadata": {},
"source": [
"### Using a configurable model declaratively\n",
"\n",
"We can call declarative operations like `bind_tools`, `with_structured_output`, `with_configurable`, etc. on a configurable model and chain a configurable model in the same way that we would a regularly instantiated chat model object."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "067dabee-1050-4110-ae24-c48eba01e13b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'name': 'GetPopulation',\n",
" 'args': {'location': 'Los Angeles, CA'},\n",
" 'id': 'call_sYT3PFMufHGWJD32Hi2CTNUP'},\n",
" {'name': 'GetPopulation',\n",
" 'args': {'location': 'New York, NY'},\n",
" 'id': 'call_j1qjhxRnD3ffQmRyqjlI1Lnk'}]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_core.pydantic_v1 import BaseModel, Field\n",
"\n",
"\n",
"class GetWeather(BaseModel):\n",
" \"\"\"Get the current weather in a given location\"\"\"\n",
"\n",
" location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
"\n",
"\n",
"class GetPopulation(BaseModel):\n",
" \"\"\"Get the current population in a given location\"\"\"\n",
"\n",
" location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
"\n",
"\n",
"llm = init_chat_model(temperature=0)\n",
"llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])\n",
"\n",
"llm_with_tools.invoke(\n",
" \"what's bigger in 2024 LA or NYC\", config={\"configurable\": {\"model\": \"gpt-4o\"}}\n",
").tool_calls"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "e57dfe9f-cd24-4e37-9ce9-ccf8daf78f89",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'name': 'GetPopulation',\n",
" 'args': {'location': 'Los Angeles, CA'},\n",
" 'id': 'toolu_01CxEHxKtVbLBrvzFS7GQ5xR'},\n",
" {'name': 'GetPopulation',\n",
" 'args': {'location': 'New York City, NY'},\n",
" 'id': 'toolu_013A79qt5toWSsKunFBDZd5S'}]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_with_tools.invoke(\n",
" \"what's bigger in 2024 LA or NYC\",\n",
" config={\"configurable\": {\"model\": \"claude-3-5-sonnet-20240620\"}},\n",
").tool_calls"
]
}
],
"metadata": {
@@ -149,7 +326,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.11.9"
}
},
"nbformat": 4,