WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-28 20:45:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

Clean up docstrings

Browse Source
This commit is contained in:
Lance Martin
2024-02-07 16:07:33 -08:00
parent 385ec91b0e
commit addc79d29d
3 changed files with 67 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/rag/langgraph_crag.ipynb
+27 -27
View File
@@ -132,12 +132,10 @@
"\n",
"class GraphState(TypedDict):\n",
" \"\"\"\n",
" Represents the state of an agent in the conversation.\n",
" Represents the state of our graph.\n",
"\n",
" Attributes:\n",
" keys: A dictionary where each key is a string and the value is expected to be a list or another structure\n",
" that supports addition with `operator.add`. This could be used, for instance, to accumulate messages\n",
" or other pieces of data throughout the graph.\n",
" keys: A dictionary where each key is a string.\n",
" \"\"\"\n",
"\n",
" keys: Dict[str, any]"
@@ -198,10 +196,10 @@
" Retrieve documents\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, documents, that contains documents.\n",
" state (dict): New key added to state, documents, that contains retrieved documents\n",
" \"\"\"\n",
" print(\"---RETRIEVE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -215,10 +213,10 @@
" Generate answer\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, generation, that contains generation.\n",
" state (dict): New key added to state, generation, that contains LLM generation\n",
" \"\"\"\n",
" print(\"---GENERATE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -250,10 +248,10 @@
" Determines whether the retrieved documents are relevant to the question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" state (dict): Updates documents key with relevant documents\n",
" \"\"\"\n",
"\n",
" print(\"---CHECK RELEVANCE---\")\n",
@@ -323,10 +321,10 @@
" Transform the query to produce a better question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New value saved to question.\n",
" state (dict): Updates question key with a re-phrased question\n",
" \"\"\"\n",
"\n",
" print(\"---TRANSFORM QUERY---\")\n",
@@ -358,13 +356,13 @@
"\n",
"def web_search(state):\n",
" \"\"\"\n",
" Web search using Tavily.\n",
" Web search based on the re-phrased question using Tavily API.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" state (dict): Web results appended to documents.\n",
" state (dict): Updates documents key with appended web results\n",
" \"\"\"\n",
"\n",
" print(\"---WEB SEARCH---\")\n",
@@ -386,13 +384,13 @@
"\n",
"def decide_to_generate(state):\n",
" \"\"\"\n",
" Determines whether to generate an answer, or re-generate a question.\n",
" Determines whether to generate an answer or re-generate a question for web search.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" str: Next node to call\n",
" \"\"\"\n",
"\n",
" print(\"---DECIDE TO GENERATE---\")\n",
@@ -412,6 +410,14 @@
" return \"generate\""
]
},
{
"cell_type": "markdown",
"id": "fa076e90-7132-4fcf-8507-db5990314c4f",
"metadata": {},
"source": [
"## Build Graph"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -490,18 +496,12 @@
"id": "a7e44593-1959-4abf-8405-5e23aa9398f5",
"metadata": {},
"source": [
"Traces -\n",
"LangSmith Traces - \n",
" \n",
"[Trace](https://smith.langchain.com/public/7e0b9569-abfe-4337-b34b-842b1f93df63/r) and [Trace](https://smith.langchain.com/public/b40c5813-7caf-4cc8-b279-ee66060b2040/r)"
"* https://smith.langchain.com/public/7e0b9569-abfe-4337-b34b-842b1f93df63/r\n",
"\n",
"* https://smith.langchain.com/public/b40c5813-7caf-4cc8-b279-ee66060b2040/r"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "69eddb3e-57f4-4eea-8e40-4822fc50c729",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
examples/rag/langgraph_crag_mistral.ipynb
+21 -20
View File
@@ -37,7 +37,7 @@
"\n",
"Here we show how to implement self-reflective RAG using `Mistral` and `LangGraph`.\n",
"\n",
"In particular, we'll focus on the approach from one paper Corrective RAG (CRAG) [here](https://arxiv.org/pdf/2401.15884.pdf).\n",
"In particular, we'll focus on the approach from one paper focused on Corrective RAG (CRAG) [here](https://arxiv.org/pdf/2401.15884.pdf).\n",
"\n",
"![Screenshot 2024-02-07 at 1.21.51 PM.png](attachment:9db7f9db-55aa-48cb-95d5-bcde3f937589.png)\n",
"\n",
@@ -127,9 +127,10 @@
"\n",
"Let's implement self-reflective RAG with some ideas from the CRAG (Corrective RAG) [paper](https://arxiv.org/pdf/2401.15884.pdf):\n",
"\n",
"* Grade documents for relevance relative to the question\n",
"* If any are irrelevant, then we will supplement the context with web search\n",
"* For web search, we will re-phrase the question and use Tavily\n",
"* Grade documents for relevance relative to the question.\n",
"* If any are irrelevant, then we will supplement the context used for generation with web search.\n",
"* For web search, we will re-phrase the question and use Tavily API.\n",
"* We will then pass retrieved documents and web results to an LLM for final answer generation.\n",
"\n",
"Here is a schematic of our graph in more detail:\n",
"\n",
@@ -144,7 +145,7 @@
"\n",
"### State\n",
"\n",
"Every node in our graph will modify `state`, which is dict that contains values (question, documents, etc) relevant to RAG."
"Every node in our graph will modify `state`, which is dict that contains values (`question`, `documents`, etc) relevant to RAG."
]
},
{
@@ -215,10 +216,10 @@
" Retrieve documents\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, documents, that contains documents.\n",
" state (dict): New key added to state, documents, that contains retrieved documents\n",
" \"\"\"\n",
" print(\"---RETRIEVE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -233,10 +234,10 @@
" Generate answer\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, generation, that contains generation.\n",
" state (dict): New key added to state, generation, that contains generation\n",
" \"\"\"\n",
" print(\"---GENERATE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -274,10 +275,10 @@
" Determines whether the retrieved documents are relevant to the question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" state (dict): Updates documents key with relevant documents\n",
" \"\"\"\n",
"\n",
" print(\"---CHECK RELEVANCE---\")\n",
@@ -356,10 +357,10 @@
" Transform the query to produce a better question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New value saved to question.\n",
" state (dict): Updates question key with a re-phrased question\n",
" \"\"\"\n",
"\n",
" print(\"---TRANSFORM QUERY---\")\n",
@@ -400,10 +401,10 @@
"\n",
"def web_search(state):\n",
" \"\"\"\n",
" Web search using Tavily.\n",
" Web search based on the re-phrased question using Tavily API.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" state (dict): Web results appended to documents.\n",
@@ -429,13 +430,13 @@
"\n",
"def decide_to_generate(state):\n",
" \"\"\"\n",
" Determines whether to generate an answer, or re-generate a question.\n",
" Determines whether to generate an answer or re-generate a question for web search.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" str: Next node to call\n",
" \"\"\"\n",
"\n",
" print(\"---DECIDE TO GENERATE---\")\n",
@@ -460,7 +461,7 @@
"id": "6096626d-dfa5-48e0-8a24-3747b298bc67",
"metadata": {},
"source": [
"## Lay out our graph"
"## Build Graph"
]
},
{
@@ -507,7 +508,7 @@
"id": "ac0a868a-f0f9-4aa9-b955-a78da2359af8",
"metadata": {},
"source": [
"## Run it\n",
"## Run\n",
"\n",
"`Mistral API -` "
]
@@ -571,7 +572,7 @@
"id": "0931b76a-3ea8-4f2f-9d27-242d48ec3fe3",
"metadata": {},
"source": [
"## Trace\n",
"## LangSmith Traces\n",
"\n",
"`Mistral API -` \n",
"\n",
examples/rag/langgraph_self_rag.ipynb
+19 -20
View File
@@ -141,12 +141,10 @@
"\n",
"class GraphState(TypedDict):\n",
" \"\"\"\n",
" Represents the state of an agent in the conversation.\n",
" Represents the state of our graph.\n",
"\n",
" Attributes:\n",
" keys: A dictionary where each key is a string and the value is expected to be a list or another structure\n",
" that supports addition with `operator.add`. This could be used, for instance, to accumulate messages\n",
" or other pieces of data throughout the graph.\n",
" keys: A dictionary where each key is a string.\n",
" \"\"\"\n",
"\n",
" keys: Dict[str, any]"
@@ -205,10 +203,10 @@
" Retrieve documents\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, documents, that contains documents.\n",
" state (dict): New key added to state, documents, that contains retrieved documents\n",
" \"\"\"\n",
" print(\"---RETRIEVE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -222,10 +220,10 @@
" Generate answer\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, generation, that contains generation.\n",
" state (dict): New key added to state, generation, that contains LLM generation\n",
" \"\"\"\n",
" print(\"---GENERATE---\")\n",
" state_dict = state[\"keys\"]\n",
@@ -257,10 +255,10 @@
" Determines whether the retrieved documents are relevant to the question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" state (dict): Updates documents key with relevant documents\n",
" \"\"\"\n",
"\n",
" print(\"---CHECK RELEVANCE---\")\n",
@@ -322,10 +320,10 @@
" Transform the query to produce a better question.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" dict: New value saved to question.\n",
" state (dict): Updates question key with a re-phrased question\n",
" \"\"\"\n",
"\n",
" print(\"---TRANSFORM QUERY---\")\n",
@@ -357,13 +355,13 @@
"\n",
"def prepare_for_final_grade(state):\n",
" \"\"\"\n",
" Stage for final grade, passthrough state.\n",
" Passthrough state for final grade.\n",
"\n",
" Args:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
"\n",
" Returns:\n",
" state (dict): The current state of the agent, including all keys.\n",
" state (dict): The current graph state\n",
" \"\"\"\n",
"\n",
" print(\"---FINAL GRADE---\")\n",
@@ -388,7 +386,7 @@
" state (dict): The current state of the agent, including all keys.\n",
"\n",
" Returns:\n",
" dict: New key added to state, filtered_documents, that contains relevant documents.\n",
" str: Next node to call\n",
" \"\"\"\n",
"\n",
" print(\"---DECIDE TO GENERATE---\")\n",
@@ -415,7 +413,7 @@
" state (dict): The current state of the agent, including all keys.\n",
"\n",
" Returns:\n",
" str: Binary decision score.\n",
" str: Binary decision\n",
" \"\"\"\n",
"\n",
" print(\"---GRADE GENERATION vs DOCUMENTS---\")\n",
@@ -479,7 +477,7 @@
" state (dict): The current state of the agent, including all keys.\n",
"\n",
" Returns:\n",
" str: Binary decision score.\n",
" str: Binary decision\n",
" \"\"\"\n",
"\n",
" print(\"---GRADE GENERATION vs QUESTION---\")\n",
@@ -540,7 +538,7 @@
"id": "61cd5797-1782-4d78-a277-8196d13f3e1b",
"metadata": {},
"source": [
"## Graph"
"## Build Graph"
]
},
{
@@ -634,9 +632,10 @@
"id": "548f1c5b-4108-4aae-8abb-ec171b511b92",
"metadata": {},
"source": [
"Trace - \n",
"LangSmith Traces - \n",
" \n",
"* https://smith.langchain.com/public/55d6180f-aab8-42bc-8799-dadce6247d9b/r\n",
"\n",
"* https://smith.langchain.com/public/f85ebc95-81d9-47fc-91c6-b54e5b78f359/r"
]
}