Skip to content

Commit bdb93a7

Browse files
eyurtsevisahers1
authored and
olgamurraft
committed
docs: Updating integration docs for Fireworks Embeddings (langchain-ai#25247)
Providers: * fireworks See related issue: * langchain-ai#24856 Features: ```json [ { "provider": "fireworks", "js": true, "local": false, "serializable": false, } ] ``` --------- Co-authored-by: isaac hershenson <ihershenson@hmc.edu> Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
1 parent 371659e commit bdb93a7

File tree

1 file changed

+182
-33
lines changed

1 file changed

+182
-33
lines changed

‎docs/docs/integrations/text_embedding/fireworks.ipynb

Lines changed: 182 additions & 33 deletions
Original file line numberDiff line numberDiff line change
@@ -1,19 +1,88 @@
11
{
22
"cells": [
3+
{
4+
"cell_type": "raw",
5+
"id": "afaf8039",
6+
"metadata": {},
7+
"source": [
8+
"---\n",
9+
"sidebar_label: Fireworks\n",
10+
"---"
11+
]
12+
},
313
{
414
"cell_type": "markdown",
5-
"id": "b14a24db",
15+
"id": "9a3d6f34",
616
"metadata": {},
717
"source": [
818
"# FireworksEmbeddings\n",
919
"\n",
10-
"This notebook explains how to use Fireworks Embeddings, which is included in the langchain_fireworks package, to embed texts in langchain. We use the default nomic-ai v1.5 model in this example."
20+
"This will help you get started with Fireworks embedding models using LangChain. For detailed documentation on `FireworksEmbeddings` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/embeddings/langchain_fireworks.embeddings.FireworksEmbeddings.html).\n",
21+
"\n",
22+
"## Overview\n",
23+
"\n",
24+
"### Integration details\n",
25+
"\n",
26+
"import { ItemTable } from \"@theme/FeatureTables\";\n",
27+
"\n",
28+
"<ItemTable category=\"text_embedding\" item=\"Fireworks\" />\n",
29+
"\n",
30+
"## Setup\n",
31+
"\n",
32+
"To access Fireworks embedding models you'll need to create a Fireworks account, get an API key, and install the `langchain-fireworks` integration package.\n",
33+
"\n",
34+
"### Credentials\n",
35+
"\n",
36+
"Head to [fireworks.ai](https://fireworks.ai/) to sign up to Fireworks and generate an API key. Once you’ve done this set the FIREWORKS_API_KEY environment variable:"
37+
]
38+
},
39+
{
40+
"cell_type": "code",
41+
"execution_count": 1,
42+
"id": "36521c2a",
43+
"metadata": {},
44+
"outputs": [],
45+
"source": [
46+
"import getpass\n",
47+
"import os\n",
48+
"\n",
49+
"if not os.getenv(\"FIREWORKS_API_KEY\"):\n",
50+
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Enter your Fireworks API key: \")"
51+
]
52+
},
53+
{
54+
"cell_type": "markdown",
55+
"id": "c84fb993",
56+
"metadata": {},
57+
"source": [
58+
"If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
59+
]
60+
},
61+
{
62+
"cell_type": "code",
63+
"execution_count": 2,
64+
"id": "39a4953b",
65+
"metadata": {},
66+
"outputs": [],
67+
"source": [
68+
"# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
69+
"# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
70+
]
71+
},
72+
{
73+
"cell_type": "markdown",
74+
"id": "d9664366",
75+
"metadata": {},
76+
"source": [
77+
"### Installation\n",
78+
"\n",
79+
"The LangChain Fireworks integration lives in the `langchain-fireworks` package:"
1180
]
1281
},
1382
{
1483
"cell_type": "code",
1584
"execution_count": null,
16-
"id": "0ab948fc",
85+
"id": "64853226",
1786
"metadata": {},
1887
"outputs": [],
1988
"source": [
@@ -22,83 +91,163 @@
2291
},
2392
{
2493
"cell_type": "markdown",
25-
"id": "67c637ca",
94+
"id": "45dd1724",
2695
"metadata": {},
2796
"source": [
28-
"## Setup"
97+
"## Instantiation\n",
98+
"\n",
99+
"Now we can instantiate our model object and generate chat completions:"
29100
]
30101
},
31102
{
32103
"cell_type": "code",
33-
"execution_count": 1,
34-
"id": "5709b030",
104+
"execution_count": 4,
105+
"id": "9ea7a09b",
35106
"metadata": {},
36107
"outputs": [],
37108
"source": [
38-
"from langchain_fireworks import FireworksEmbeddings"
109+
"from langchain_fireworks import FireworksEmbeddings\n",
110+
"\n",
111+
"embeddings = FireworksEmbeddings(\n",
112+
" model=\"nomic-ai/nomic-embed-text-v1.5\",\n",
113+
")"
114+
]
115+
},
116+
{
117+
"cell_type": "markdown",
118+
"id": "77d271b6",
119+
"metadata": {},
120+
"source": [
121+
"## Indexing and Retrieval\n",
122+
"\n",
123+
"Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our RAG tutorials under the [working with external knowledge tutorials](/docs/tutorials/#working-with-external-knowledge).\n",
124+
"\n",
125+
"Below, see how to index and retrieve data using the `embeddings` object we initialized above. In this example, we will index and retrieve a sample document in the `InMemoryVectorStore`."
39126
]
40127
},
41128
{
42129
"cell_type": "code",
43-
"execution_count": 2,
44-
"id": "3d81e58c",
130+
"execution_count": 5,
131+
"id": "d817716b",
45132
"metadata": {},
46-
"outputs": [],
133+
"outputs": [
134+
{
135+
"data": {
136+
"text/plain": [
137+
"'LangChain is the framework for building context-aware reasoning applications'"
138+
]
139+
},
140+
"execution_count": 5,
141+
"metadata": {},
142+
"output_type": "execute_result"
143+
}
144+
],
47145
"source": [
48-
"import getpass\n",
49-
"import os\n",
146+
"# Create a vector store with a sample text\n",
147+
"from langchain_core.vectorstores import InMemoryVectorStore\n",
148+
"\n",
149+
"text = \"LangChain is the framework for building context-aware reasoning applications\"\n",
150+
"\n",
151+
"vectorstore = InMemoryVectorStore.from_texts(\n",
152+
" [text],\n",
153+
" embedding=embeddings,\n",
154+
")\n",
50155
"\n",
51-
"if \"FIREWORKS_API_KEY\" not in os.environ:\n",
52-
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")"
156+
"# Use the vectorstore as a retriever\n",
157+
"retriever = vectorstore.as_retriever()\n",
158+
"\n",
159+
"# Retrieve the most similar text\n",
160+
"retrieved_documents = retriever.invoke(\"What is LangChain?\")\n",
161+
"\n",
162+
"# show the retrieved document's content\n",
163+
"retrieved_documents[0].page_content"
53164
]
54165
},
55166
{
56167
"cell_type": "markdown",
57-
"id": "4a2a098d",
168+
"id": "e02b9855",
58169
"metadata": {},
59170
"source": [
60-
"# Using the Embedding Model\n",
61-
"With `FireworksEmbeddings`, you can directly use the default model 'nomic-ai/nomic-embed-text-v1.5', or set a different one if available."
171+
"## Direct Usage\n",
172+
"\n",
173+
"Under the hood, the vectorstore and retriever implementations are calling `embeddings.embed_documents(...)` and `embeddings.embed_query(...)` to create embeddings for the text(s) used in `from_texts` and retrieval `invoke` operations, respectively.\n",
174+
"\n",
175+
"You can directly call these methods to get embeddings for your own use cases.\n",
176+
"\n",
177+
"### Embed single texts\n",
178+
"\n",
179+
"You can embed single texts or documents with `embed_query`:"
62180
]
63181
},
64182
{
65183
"cell_type": "code",
66-
"execution_count": 3,
67-
"id": "584b9af5",
184+
"execution_count": 6,
185+
"id": "0d2befcd",
186+
"metadata": {},
187+
"outputs": [
188+
{
189+
"name": "stdout",
190+
"output_type": "stream",
191+
"text": [
192+
"[0.01666259765625, 0.011688232421875, -0.1181640625, -0.10205078125, 0.05438232421875, -0.0890502929\n"
193+
]
194+
}
195+
],
196+
"source": [
197+
"single_vector = embeddings.embed_query(text)\n",
198+
"print(str(single_vector)[:100]) # Show the first 100 characters of the vector"
199+
]
200+
},
201+
{
202+
"cell_type": "markdown",
203+
"id": "1b5a7d03",
68204
"metadata": {},
69-
"outputs": [],
70205
"source": [
71-
"embedding = FireworksEmbeddings(model=\"nomic-ai/nomic-embed-text-v1.5\")"
206+
"### Embed multiple texts\n",
207+
"\n",
208+
"You can embed multiple texts with `embed_documents`:"
72209
]
73210
},
74211
{
75212
"cell_type": "code",
76-
"execution_count": 4,
77-
"id": "be18b873",
213+
"execution_count": 7,
214+
"id": "2f4d6e97",
78215
"metadata": {},
79216
"outputs": [
80217
{
81218
"name": "stdout",
82219
"output_type": "stream",
83220
"text": [
84-
"[0.01367950439453125, 0.0103607177734375, -0.157958984375, -0.003070831298828125, 0.05926513671875]\n",
85-
"[0.0369873046875, 0.00545501708984375, -0.179931640625, -0.018707275390625, 0.0552978515625]\n"
221+
"[0.016632080078125, 0.01165008544921875, -0.1181640625, -0.10186767578125, 0.05438232421875, -0.0890\n",
222+
"[-0.02667236328125, 0.036651611328125, -0.1630859375, -0.0904541015625, -0.022430419921875, -0.09545\n"
86223
]
87224
}
88225
],
89226
"source": [
90-
"res_query = embedding.embed_query(\"The test information\")\n",
91-
"res_document = embedding.embed_documents([\"test1\", \"another test\"])\n",
92-
"print(res_query[:5])\n",
93-
"print(res_document[1][:5])"
227+
"text2 = (\n",
228+
" \"LangGraph is a library for building stateful, multi-actor applications with LLMs\"\n",
229+
")\n",
230+
"two_vectors = embeddings.embed_documents([text, text2])\n",
231+
"for vector in two_vectors:\n",
232+
" print(str(vector)[:100]) # Show the first 100 characters of the vector"
233+
]
234+
},
235+
{
236+
"cell_type": "markdown",
237+
"id": "3fba556a-b53d-431c-b0c6-ffb1e2fa5a6e",
238+
"metadata": {},
239+
"source": [
240+
"## API Reference\n",
241+
"\n",
242+
"For detailed documentation of all `FireworksEmbeddings` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/embeddings/langchain_fireworks.embeddings.FireworksEmbeddings.html)."
94243
]
95244
}
96245
],
97246
"metadata": {
98247
"kernelspec": {
99-
"display_name": "poetry-venv-2",
248+
"display_name": "Python 3 (ipykernel)",
100249
"language": "python",
101-
"name": "poetry-venv-2"
250+
"name": "python3"
102251
},
103252
"language_info": {
104253
"codemirror_mode": {
@@ -110,7 +259,7 @@
110259
"name": "python",
111260
"nbconvert_exporter": "python",
112261
"pygments_lexer": "ipython3",
113-
"version": "3.9.1"
262+
"version": "3.11.4"
114263
}
115264
},
116265
"nbformat": 4,

0 commit comments

Comments
 (0)