github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 04:07:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding LangChain v0.2 support for nvidia ai endpoint, langchain-nvidia-ai-endpoints. Removed deprecated classes from nvidia_ai_endpoints.ipynb (#24411)

Browse Source 
Description: added support for LangChain v0.2 for nvidia ai endpoint.
Implremented inMemory storage for chains using
RunnableWithMessageHistory which is analogous to using
`ConversationChain` which was used in v0.1 with the default
`ConversationBufferMemory`. This class is deprecated in favor of
`RunnableWithMessageHistory` in LangChain v0.2

Issue: None

Dependencies: None.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
Srijan Dubey 2024-07-19 01:29:26 +05:30 committed by GitHub
parent 334fc1ed1c
commit 4c651ba13a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 39 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb
View File

@ -540,7 +540,7 @@
"id": "137662a6" "id": "137662a6"
}, },
"source": [ "source": [
"## Example usage within a Conversation Chains" "## Example usage within RunnableWithMessageHistory "
] ]
}, },
{ {
@ -550,7 +550,7 @@
"id": "79efa62d" "id": "79efa62d"
}, },
"source": [ "source": [
"Like any other integration, ChatNVIDIA is fine to support chat utilities like conversation buffers by default. Below, we show the [LangChain ConversationBufferMemory](https://python.langchain.com/docs/modules/memory/types/buffer) example applied to the `mistralai/mixtral-8x22b-instruct-v0.1` model." "Like any other integration, ChatNVIDIA is fine to support chat utilities like RunnableWithMessageHistory which is analogous to using `ConversationChain`. Below, we show the [LangChain RunnableWithMessageHistory](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html) example applied to the `mistralai/mixtral-8x22b-instruct-v0.1` model."
] ]
}, },
{ {
@ -572,8 +572,19 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"from langchain.chains import ConversationChain\n", "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
"from langchain.memory import ConversationBufferMemory\n", "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
"\n",
"# store is a dictionary that maps session IDs to their corresponding chat histories.\n",
"store = {} # memory is maintained outside the chain\n",
"\n",
"\n",
"# A function that returns the chat history for a given session ID.\n",
"def get_session_history(session_id: str) -> InMemoryChatMessageHistory:\n",
" if session_id not in store:\n",
" store[session_id] = InMemoryChatMessageHistory()\n",
" return store[session_id]\n",
"\n",
"\n", "\n",
"chat = ChatNVIDIA(\n", "chat = ChatNVIDIA(\n",
" model=\"mistralai/mixtral-8x22b-instruct-v0.1\",\n", " model=\"mistralai/mixtral-8x22b-instruct-v0.1\",\n",
@ -582,24 +593,18 @@
" top_p=1.0,\n", " top_p=1.0,\n",
")\n", ")\n",
"\n", "\n",
"conversation = ConversationChain(llm=chat, memory=ConversationBufferMemory())" "# Define a RunnableConfig object, with a `configurable` key. session_id determines thread\n",
] "config = {\"configurable\": {\"session_id\": \"1\"}}\n",
}, "\n",
{ "conversation = RunnableWithMessageHistory(\n",
"cell_type": "code", " chat,\n",
"execution_count": null, " get_session_history,\n",
"id": "f644ff28", ")\n",
"metadata": { "\n",
"colab": { "conversation.invoke(\n",
"base_uri": "https://localhost:8080/", " \"Hi I'm Srijan Dubey.\", # input or query\n",
"height": 268 " config=config,\n",
}, ")"
"id": "f644ff28",
"outputId": "bae354cc-2118-4e01-ce20-a717ac94d27d"
},
"outputs": [],
"source": [
"conversation.invoke(\"Hi there!\")[\"response\"]"
] ]
}, },
{ {
@ -616,26 +621,30 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"conversation.invoke(\"I'm doing well! Just having a conversation with an AI.\")[\n", "conversation.invoke(\n",
" \"response\"\n", " \"I'm doing well! Just having a conversation with an AI.\",\n",
"]" " config=config,\n",
")"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "LyD1xVKmVSs4", "id": "uHIMZxVSVNBC",
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
"height": 350 "height": 284
}, },
"id": "LyD1xVKmVSs4", "id": "uHIMZxVSVNBC",
"outputId": "a1714513-a8fd-4d14-f974-233e39d5c4f5" "outputId": "79acc89d-a820-4f2c-bac2-afe99da95580"
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"conversation.invoke(\"Tell me about yourself.\")[\"response\"]" "conversation.invoke(\n",
" \"Tell me about yourself.\",\n",
" config=config,\n",
")"
] ]
} }
], ],