Skip to content

Commit 52a8dc0

Browse files
ppradospprados
authored
Merge branch 'master' into pprados/pdf-router
2 parents 5c2f21b + b36c2bf commit 52a8dc0

File tree

32 files changed

+801
-444
lines changed

32 files changed

+801
-444
lines changed

‎docs/api_reference/conf.py

+4
Original file line numberDiff line numberDiff line change
@@ -275,3 +275,7 @@ def skip_private_members(app, what, name, obj, skip, options):
275275
html_context["READTHEDOCS"] = True
276276

277277
master_doc = "index"
278+
279+
# If a signature’s length in characters exceeds 60,
280+
# each parameter within the signature will be displayed on an individual logical line
281+
maximum_signature_line_length = 60

‎docs/docs/integrations/chat/bedrock.ipynb

+389-366
Large diffs are not rendered by default.

‎docs/docs/integrations/chat/openai.ipynb

+72-1
Original file line numberDiff line numberDiff line change
@@ -408,7 +408,7 @@
408408
"\n",
409409
":::\n",
410410
"\n",
411-
"OpenAI supports a [Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions) API that is oriented toward building [agentic](/docs/concepts/agents/) applications. It includes a suite of [built-in tools](https://platform.openai.com/docs/guides/tools?api-mode=responses), including web and file search. It also supports management of [conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses), allowing you to continue a conversational thread without explicitly passing in previous messages.\n",
411+
"OpenAI supports a [Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions) API that is oriented toward building [agentic](/docs/concepts/agents/) applications. It includes a suite of [built-in tools](https://platform.openai.com/docs/guides/tools?api-mode=responses), including web and file search. It also supports management of [conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses), allowing you to continue a conversational thread without explicitly passing in previous messages, as well as the output from [reasoning processes](https://platform.openai.com/docs/guides/reasoning?api-mode=responses).\n",
412412
"\n",
413413
"`ChatOpenAI` will route to the Responses API if one of these features is used. You can also specify `use_responses_api=True` when instantiating `ChatOpenAI`.\n",
414414
"\n",
@@ -1056,6 +1056,77 @@
10561056
"print(second_response.text())"
10571057
]
10581058
},
1059+
{
1060+
"cell_type": "markdown",
1061+
"id": "67bf5bd2-0935-40a0-b1cd-c6662b681d4b",
1062+
"metadata": {},
1063+
"source": [
1064+
"### Reasoning output\n",
1065+
"\n",
1066+
"Some OpenAI models will generate separate text content illustrating their reasoning process. See OpenAI's [reasoning documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses) for details.\n",
1067+
"\n",
1068+
"OpenAI can return a summary of the model's reasoning (although it doesn't expose the raw reasoning tokens). To configure `ChatOpenAI` to return this summary, specify the `reasoning` parameter:"
1069+
]
1070+
},
1071+
{
1072+
"cell_type": "code",
1073+
"execution_count": 2,
1074+
"id": "8d322f3a-0732-45ab-ac95-dfd4596e0d85",
1075+
"metadata": {},
1076+
"outputs": [
1077+
{
1078+
"data": {
1079+
"text/plain": [
1080+
"'3^3 = 3 × 3 × 3 = 27.'"
1081+
]
1082+
},
1083+
"execution_count": 2,
1084+
"metadata": {},
1085+
"output_type": "execute_result"
1086+
}
1087+
],
1088+
"source": [
1089+
"from langchain_openai import ChatOpenAI\n",
1090+
"\n",
1091+
"reasoning = {\n",
1092+
" \"effort\": \"medium\", # 'low', 'medium', or 'high'\n",
1093+
" \"summary\": \"auto\", # 'detailed', 'auto', or None\n",
1094+
"}\n",
1095+
"\n",
1096+
"llm = ChatOpenAI(\n",
1097+
" model=\"o4-mini\",\n",
1098+
" use_responses_api=True,\n",
1099+
" model_kwargs={\"reasoning\": reasoning},\n",
1100+
")\n",
1101+
"response = llm.invoke(\"What is 3^3?\")\n",
1102+
"\n",
1103+
"# Output\n",
1104+
"response.text()"
1105+
]
1106+
},
1107+
{
1108+
"cell_type": "code",
1109+
"execution_count": 3,
1110+
"id": "d7dcc082-b7c8-41b7-a5e2-441b9679e41b",
1111+
"metadata": {},
1112+
"outputs": [
1113+
{
1114+
"name": "stdout",
1115+
"output_type": "stream",
1116+
"text": [
1117+
"**Calculating power of three**\n",
1118+
"\n",
1119+
"The user is asking for the result of 3 to the power of 3, which I know is 27. It's a straightforward question, so I’ll keep my answer concise: 27. I could explain that this is the same as multiplying 3 by itself twice: 3 × 3 × 3 equals 27. However, since the user likely just needs the answer, I’ll simply respond with 27.\n"
1120+
]
1121+
}
1122+
],
1123+
"source": [
1124+
"# Reasoning\n",
1125+
"reasoning = response.additional_kwargs[\"reasoning\"]\n",
1126+
"for block in reasoning[\"summary\"]:\n",
1127+
" print(block[\"text\"])"
1128+
]
1129+
},
10591130
{
10601131
"cell_type": "markdown",
10611132
"id": "57e27714",

‎docs/docs/integrations/providers/aws.mdx

+11-2
Original file line numberDiff line numberDiff line change
@@ -35,9 +35,18 @@ from langchain_aws import ChatBedrock
3535
```
3636

3737
### Bedrock Converse
38-
AWS has recently released the Bedrock Converse API which provides a unified conversational interface for Bedrock models. This API does not yet support custom models. You can see a list of all [models that are supported here](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html). To improve reliability the ChatBedrock integration will switch to using the Bedrock Converse API as soon as it has feature parity with the existing Bedrock API. Until then a separate [ChatBedrockConverse](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html) integration has been released.
38+
AWS Bedrock maintains a [Converse API](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html)
39+
that provides a unified conversational interface for Bedrock models. This API does not
40+
yet support custom models. You can see a list of all
41+
[models that are supported here](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html).
3942

40-
We recommend using `ChatBedrockConverse` for users who do not need to use custom models. See the [docs](/docs/integrations/chat/bedrock/#bedrock-converse-api) and [API reference](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html) for more detail.
43+
:::info
44+
45+
We recommend the Converse API for users who do not need to use custom models. It can be accessed using [ChatBedrockConverse](https://python.langchain.com/api_reference/aws/chat_models/langchain_aws.chat_models.bedrock_converse.ChatBedrockConverse.html).
46+
47+
:::
48+
49+
See a [usage example](/docs/integrations/chat/bedrock).
4150

4251
```python
4352
from langchain_aws import ChatBedrockConverse

‎docs/docs/integrations/providers/galaxia.mdx

+32
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,32 @@
1+
# Smabbler
2+
> Smabbler’s graph-powered platform boosts AI development by transforming data into a structured knowledge foundation.
3+
4+
# Galaxia
5+
6+
> Galaxia Knowledge Base is an integrated knowledge base and retrieval mechanism for RAG. In contrast to standard solution, it is based on Knowledge Graphs built using symbolic NLP and Knowledge Representation solutions. Provided texts are analysed and transformed into Graphs containing text, language and semantic information. This rich structure allows for retrieval that is based on semantic information, not on vector similarity/distance.
7+
8+
Implementing RAG using Galaxia involves first uploading your files to [Galaxia](https://beta.cloud.smabbler.com/home), analyzing them there and then building a model (knowledge graph). When the model is built, you can use `GalaxiaRetriever` to connect to the API and start retrieving.
9+
10+
More information: [docs](https://smabbler.gitbook.io/smabbler)
11+
12+
## Installation
13+
```
14+
pip install langchain-galaxia-retriever
15+
```
16+
17+
## Usage
18+
19+
```
20+
from langchain_galaxia_retriever.retriever import GalaxiaRetriever
21+
22+
gr = GalaxiaRetriever(
23+
api_url="beta.api.smabbler.com",
24+
api_key="<key>",
25+
knowledge_base_id="<knowledge_base_id>",
26+
n_retries=10,
27+
wait_time=5,
28+
)
29+
30+
result = gr.invoke('<test question>')
31+
print(result)
32+

‎docs/docs/integrations/retrievers/galaxia-retriever.ipynb

+213
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,213 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "raw",
5+
"id": "2af1fec5-4ca6-4167-8ee1-13314aac3258",
6+
"metadata": {
7+
"vscode": {
8+
"languageId": "raw"
9+
}
10+
},
11+
"source": [
12+
"---\n",
13+
"sidebar_label: Galaxia\n",
14+
"---"
15+
]
16+
},
17+
{
18+
"cell_type": "markdown",
19+
"id": "1d7d6cbc-4373-4fb5-94dd-acd610165452",
20+
"metadata": {},
21+
"source": [
22+
"# Galaxia Retriever\n",
23+
"\n",
24+
"Galaxia is GraphRAG solution, which automates document processing, knowledge base (Graph Language Model) creation and retrieval:\n",
25+
"[galaxia-rag](https://smabbler.gitbook.io/smabbler/api-rag/smabblers-api-rag)\n",
26+
"\n",
27+
"To use Galaxia first upload your texts and create a Graph Language Model here: [smabbler-cloud](https://beta.cloud.smabbler.com)\n",
28+
"\n",
29+
"After the model is built and activated, you will be able to use this integration to retrieve what you need.\n",
30+
"\n",
31+
"The module repository is located here: [github](https://github.com/rrozanski-smabbler/galaxia-langchain)\n",
32+
"\n",
33+
"### Integration details\n",
34+
"| Retriever | Self-host | Cloud offering | Package |\n",
35+
"| :--- | :--- | :---: | :---: |\n",
36+
"[Galaxia Retriever](https://github.com/rrozanski-smabbler/galaxia-langchain) | ❌ | ✅ | __langchain-galaxia-retriever__ |"
37+
]
38+
},
39+
{
40+
"cell_type": "markdown",
41+
"id": "82fa1c05-c205-4429-a74c-e6c81c4e8611",
42+
"metadata": {},
43+
"source": [
44+
"## Setup\n",
45+
"Before you can retrieve anything you need to create your Graph Language Model here: [smabbler-cloud](https://beta.cloud.smabbler.com)\n",
46+
"\n",
47+
"following these 3 simple steps: [rag-instruction](https://smabbler.gitbook.io/smabbler/api-rag/build-rag-model-in-3-steps)\n",
48+
"\n",
49+
"Don't forget to activate the model after building it!"
50+
]
51+
},
52+
{
53+
"cell_type": "markdown",
54+
"id": "91897867-eb39-4c3b-8df8-5427043ecdcd",
55+
"metadata": {},
56+
"source": [
57+
"### Installation\n",
58+
"The retriever is implemented in the following package: [pypi](https://pypi.org/project/langchain-galaxia-retriever/)"
59+
]
60+
},
61+
{
62+
"cell_type": "code",
63+
"execution_count": null,
64+
"id": "ceca36f2-013c-4b28-81fe-8808d0cf6419",
65+
"metadata": {},
66+
"outputs": [],
67+
"source": [
68+
"%pip install -qU langchain-galaxia-retriever"
69+
]
70+
},
71+
{
72+
"cell_type": "markdown",
73+
"id": "019e0e50-5e66-440b-9cf1-d21b4009bf13",
74+
"metadata": {},
75+
"source": [
76+
"## Instantiation"
77+
]
78+
},
79+
{
80+
"cell_type": "code",
81+
"execution_count": null,
82+
"id": "c7188217-4b26-4201-b15a-b7a5f263f815",
83+
"metadata": {},
84+
"outputs": [],
85+
"source": [
86+
"from langchain_galaxia_retriever.retriever import GalaxiaRetriever\n",
87+
"\n",
88+
"gr = GalaxiaRetriever(\n",
89+
" api_url=\"beta.api.smabbler.com\",\n",
90+
" api_key=\"<key>\", # you can find it here: https://beta.cloud.smabbler.com/user/account\n",
91+
" knowledge_base_id=\"<knowledge_base_id>\", # you can find it in https://beta.cloud.smabbler.com , in the model table\n",
92+
" n_retries=10,\n",
93+
" wait_time=5,\n",
94+
")"
95+
]
96+
},
97+
{
98+
"cell_type": "markdown",
99+
"id": "02d288a5-4f76-472e-9a60-eea8e6b8dc7a",
100+
"metadata": {},
101+
"source": [
102+
"## Usage"
103+
]
104+
},
105+
{
106+
"cell_type": "code",
107+
"execution_count": null,
108+
"id": "5f79e03f-77a6-4eb6-b41d-f3da2f897654",
109+
"metadata": {},
110+
"outputs": [],
111+
"source": [
112+
"result = gr.invoke(\"<test question>\")\n",
113+
"print(result)"
114+
]
115+
},
116+
{
117+
"cell_type": "markdown",
118+
"id": "ffb2a595-a901-477a-a374-efd091bc1c9a",
119+
"metadata": {},
120+
"source": [
121+
"## Use within a chain"
122+
]
123+
},
124+
{
125+
"cell_type": "code",
126+
"execution_count": null,
127+
"id": "9c2e2394-ca33-47be-a851-551b4216daea",
128+
"metadata": {},
129+
"outputs": [],
130+
"source": [
131+
"# | output: false\n",
132+
"# | echo: false\n",
133+
"\n",
134+
"from langchain_openai import ChatOpenAI\n",
135+
"\n",
136+
"llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
137+
]
138+
},
139+
{
140+
"cell_type": "code",
141+
"execution_count": null,
142+
"id": "ed8699d6-d65d-40ea-8c58-8d809cc512cf",
143+
"metadata": {},
144+
"outputs": [],
145+
"source": [
146+
"from langchain_core.output_parsers import StrOutputParser\n",
147+
"from langchain_core.prompts import ChatPromptTemplate\n",
148+
"from langchain_core.runnables import RunnablePassthrough\n",
149+
"\n",
150+
"prompt = ChatPromptTemplate.from_template(\n",
151+
" \"\"\"Answer the question based only on the context provided.\n",
152+
"\n",
153+
"Context: {context}\n",
154+
"\n",
155+
"Question: {question}\"\"\"\n",
156+
")\n",
157+
"\n",
158+
"\n",
159+
"def format_docs(docs):\n",
160+
" return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
161+
"\n",
162+
"\n",
163+
"chain = (\n",
164+
" {\"context\": gr | format_docs, \"question\": RunnablePassthrough()}\n",
165+
" | prompt\n",
166+
" | llm\n",
167+
" | StrOutputParser()\n",
168+
")"
169+
]
170+
},
171+
{
172+
"cell_type": "code",
173+
"execution_count": null,
174+
"id": "f9b944d7-8800-4926-b1ce-fcdc52ecda1c",
175+
"metadata": {},
176+
"outputs": [],
177+
"source": [
178+
"chain.invoke(\"<test question>\")"
179+
]
180+
},
181+
{
182+
"cell_type": "markdown",
183+
"id": "11b5c9a5-0a66-415f-98f8-f12080cad30a",
184+
"metadata": {},
185+
"source": [
186+
"## API reference\n",
187+
"\n",
188+
"For more information about Galaxia Retriever check its implementation on github [github](https://github.com/rrozanski-smabbler/galaxia-langchain)"
189+
]
190+
}
191+
],
192+
"metadata": {
193+
"kernelspec": {
194+
"display_name": "Python 3 (ipykernel)",
195+
"language": "python",
196+
"name": "python3"
197+
},
198+
"language_info": {
199+
"codemirror_mode": {
200+
"name": "ipython",
201+
"version": 3
202+
},
203+
"file_extension": ".py",
204+
"mimetype": "text/x-python",
205+
"name": "python",
206+
"nbconvert_exporter": "python",
207+
"pygments_lexer": "ipython3",
208+
"version": "3.11.7"
209+
}
210+
},
211+
"nbformat": 4,
212+
"nbformat_minor": 5
213+
}

‎libs/core/langchain_core/messages/ai.py

-3
Original file line numberDiff line numberDiff line change
@@ -276,9 +276,6 @@ def _format_tool_args(tc: Union[ToolCall, InvalidToolCall]) -> list[str]:
276276
return (base.strip() + "\n" + "\n".join(lines)).strip()
277277

278278

279-
AIMessage.model_rebuild()
280-
281-
282279
class AIMessageChunk(AIMessage, BaseMessageChunk):
283280
"""Message chunk from an AI."""
284281

‎libs/core/langchain_core/messages/chat.py

-3
Original file line numberDiff line numberDiff line change
@@ -22,9 +22,6 @@ class ChatMessage(BaseMessage):
2222
"""The type of the message (used during serialization). Defaults to "chat"."""
2323

2424

25-
ChatMessage.model_rebuild()
26-
27-
2825
class ChatMessageChunk(ChatMessage, BaseMessageChunk):
2926
"""Chat Message chunk."""
3027

‎libs/core/langchain_core/messages/function.py

-3
Original file line numberDiff line numberDiff line change
@@ -30,9 +30,6 @@ class FunctionMessage(BaseMessage):
3030
"""The type of the message (used for serialization). Defaults to "function"."""
3131

3232

33-
FunctionMessage.model_rebuild()
34-
35-
3633
class FunctionMessageChunk(FunctionMessage, BaseMessageChunk):
3734
"""Function Message chunk."""
3835

0 commit comments

Comments
 (0)