Skip to content

Commit 0f557d3

Browse files
bracesproulbracesproul
authored
docs[minor],community[patch]: Update fireworks embeddings doc, add model param (#6360)
* docs[minor],community[patch]: Update fireworks embeddings doc, add model param * run cells
1 parent 134301e commit 0f557d3

File tree

3 files changed

+357
-32
lines changed

3 files changed

+357
-32
lines changed

‎docs/core_docs/docs/integrations/text_embedding/fireworks.ipynb

+344
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,344 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "raw",
5+
"id": "afaf8039",
6+
"metadata": {
7+
"vscode": {
8+
"languageId": "raw"
9+
}
10+
},
11+
"source": [
12+
"---\n",
13+
"sidebar_label: Fireworks\n",
14+
"---"
15+
]
16+
},
17+
{
18+
"cell_type": "markdown",
19+
"id": "9a3d6f34",
20+
"metadata": {},
21+
"source": [
22+
"# FireworksEmbeddings\n",
23+
"\n",
24+
"This will help you get started with FireworksEmbeddings [embedding models](/docs/concepts#embedding-models) using LangChain. For detailed documentation on `FireworksEmbeddings` features and configuration options, please refer to the [API reference](https://api.js.langchain.com/classes/langchain_community_embeddings_fireworks.FireworksEmbeddings.html).\n",
25+
"\n",
26+
"## Overview\n",
27+
"### Integration details\n",
28+
"\n",
29+
"| Class | Package | Local | [Py support](https://python.langchain.com/docs/integrations/text_embedding/fireworks/) | Package downloads | Package latest |\n",
30+
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
31+
"| [FireworksEmbeddings](https://api.js.langchain.com/classes/langchain_community_embeddings_fireworks.FireworksEmbeddings.html) | [@langchain/community](https://api.js.langchain.com/modules/langchain_community_embeddings_fireworks.html) | ❌ | ✅ | ![NPM - Downloads](https://img.shields.io/npm/dm/@langchain/community?style=flat-square&label=%20&) | ![NPM - Version](https://img.shields.io/npm/v/@langchain/community?style=flat-square&label=%20&) |\n",
32+
"\n",
33+
"## Setup\n",
34+
"\n",
35+
"To access Fireworks embedding models you'll need to create a Fireworks account, get an API key, and install the `@langchain/community` integration package.\n",
36+
"\n",
37+
"### Credentials\n",
38+
"\n",
39+
"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:\n",
40+
"\n",
41+
"```bash\n",
42+
"export FIREWORKS_API_KEY=\"your-api-key\"\n",
43+
"```\n",
44+
"\n",
45+
"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:\n",
46+
"\n",
47+
"```bash\n",
48+
"# export LANGCHAIN_TRACING_V2=\"true\"\n",
49+
"# export LANGCHAIN_API_KEY=\"your-api-key\"\n",
50+
"```\n",
51+
"\n",
52+
"### Installation\n",
53+
"\n",
54+
"The LangChain `FireworksEmbeddings` integration lives in the `@langchain/community` package:\n",
55+
"\n",
56+
"```{=mdx}\n",
57+
"import IntegrationInstallTooltip from \"@mdx_components/integration_install_tooltip.mdx\";\n",
58+
"import Npm2Yarn from \"@theme/Npm2Yarn\";\n",
59+
"\n",
60+
"<IntegrationInstallTooltip></IntegrationInstallTooltip>\n",
61+
"\n",
62+
"<Npm2Yarn>\n",
63+
" @langchain/community\n",
64+
"</Npm2Yarn>\n",
65+
"```"
66+
]
67+
},
68+
{
69+
"cell_type": "markdown",
70+
"id": "45dd1724",
71+
"metadata": {},
72+
"source": [
73+
"## Instantiation\n",
74+
"\n",
75+
"Now we can instantiate our model object and generate chat completions:"
76+
]
77+
},
78+
{
79+
"cell_type": "code",
80+
"execution_count": 1,
81+
"id": "9ea7a09b",
82+
"metadata": {},
83+
"outputs": [],
84+
"source": [
85+
"import { FireworksEmbeddings } from \"@langchain/community/embeddings/fireworks\";\n",
86+
"\n",
87+
"const embeddings = new FireworksEmbeddings({\n",
88+
" modelName: \"nomic-ai/nomic-embed-text-v1.5\",\n",
89+
"});"
90+
]
91+
},
92+
{
93+
"cell_type": "markdown",
94+
"id": "77d271b6",
95+
"metadata": {},
96+
"source": [
97+
"## Indexing and Retrieval\n",
98+
"\n",
99+
"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",
100+
"\n",
101+
"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 using the demo [`MemoryVectorStore`](/docs/integrations/vectorstores/memory)."
102+
]
103+
},
104+
{
105+
"cell_type": "code",
106+
"execution_count": 2,
107+
"id": "d817716b",
108+
"metadata": {},
109+
"outputs": [
110+
{
111+
"data": {
112+
"text/plain": [
113+
"\u001b[32m\"LangChain is the framework for building context-aware reasoning applications\"\u001b[39m"
114+
]
115+
},
116+
"execution_count": 2,
117+
"metadata": {},
118+
"output_type": "execute_result"
119+
}
120+
],
121+
"source": [
122+
"// Create a vector store with a sample text\n",
123+
"import { MemoryVectorStore } from \"langchain/vectorstores/memory\";\n",
124+
"\n",
125+
"const text = \"LangChain is the framework for building context-aware reasoning applications\";\n",
126+
"\n",
127+
"const vectorstore = await MemoryVectorStore.fromDocuments(\n",
128+
" [{ pageContent: text, metadata: {} }],\n",
129+
" embeddings,\n",
130+
");\n",
131+
"\n",
132+
"// Use the vector store as a retriever that returns a single document\n",
133+
"const retriever = vectorstore.asRetriever(1);\n",
134+
"\n",
135+
"// Retrieve the most similar text\n",
136+
"const retrievedDocuments = await retriever.invoke(\"What is LangChain?\");\n",
137+
"\n",
138+
"retrievedDocuments[0].pageContent;"
139+
]
140+
},
141+
{
142+
"cell_type": "markdown",
143+
"id": "e02b9855",
144+
"metadata": {},
145+
"source": [
146+
"## Direct Usage\n",
147+
"\n",
148+
"Under the hood, the vectorstore and retriever implementations are calling `embeddings.embedDocument(...)` and `embeddings.embedQuery(...)` to create embeddings for the text(s) used in `fromDocuments` and the retriever's `invoke` operations, respectively.\n",
149+
"\n",
150+
"You can directly call these methods to get embeddings for your own use cases.\n",
151+
"\n",
152+
"### Embed single texts\n",
153+
"\n",
154+
"You can embed queries for search with `embedQuery`. This generates a vector representation specific to the query:"
155+
]
156+
},
157+
{
158+
"cell_type": "code",
159+
"execution_count": 3,
160+
"id": "0d2befcd",
161+
"metadata": {},
162+
"outputs": [
163+
{
164+
"name": "stdout",
165+
"output_type": "stream",
166+
"text": [
167+
"[\n",
168+
" 0.01666259765625, 0.011688232421875, -0.1181640625,\n",
169+
" -0.10205078125, 0.05438232421875, -0.08905029296875,\n",
170+
" -0.018096923828125, 0.00952911376953125, -0.08056640625,\n",
171+
" -0.0283050537109375, -0.01512908935546875, 0.0312042236328125,\n",
172+
" 0.08197021484375, 0.022552490234375, 0.0012683868408203125,\n",
173+
" 0.0133056640625, -0.04327392578125, -0.004322052001953125,\n",
174+
" -0.02410888671875, -0.0012350082397460938, -0.04632568359375,\n",
175+
" 0.02996826171875, -0.0134124755859375, -0.037811279296875,\n",
176+
" 0.07672119140625, 0.021759033203125, 0.0179290771484375,\n",
177+
" -0.0002741813659667969, -0.0582275390625, -0.0224456787109375,\n",
178+
" 0.0027675628662109375, -0.017425537109375, -0.01520538330078125,\n",
179+
" -0.01146697998046875, -0.055267333984375, -0.083984375,\n",
180+
" 0.056793212890625, -0.003383636474609375, -0.034271240234375,\n",
181+
" 0.05108642578125, -0.01018524169921875, 0.0462646484375,\n",
182+
" 0.0012178421020507812, 0.005779266357421875, 0.0684814453125,\n",
183+
" 0.00797271728515625, -0.0176544189453125, 0.00257110595703125,\n",
184+
" 0.059539794921875, -0.06573486328125, -0.075439453125,\n",
185+
" -0.0247344970703125, -0.0276947021484375, 0.003940582275390625,\n",
186+
" 0.02630615234375, 0.0660400390625, 0.0157470703125,\n",
187+
" 0.033050537109375, -0.0478515625, -0.03338623046875,\n",
188+
" 0.050384521484375, 0.07757568359375, -0.045166015625,\n",
189+
" 0.07586669921875, 0.0021915435791015625, 0.0237579345703125,\n",
190+
" -0.052703857421875, 0.05023193359375, -0.0274810791015625,\n",
191+
" -0.0025081634521484375, 0.019287109375, -0.03802490234375,\n",
192+
" 0.0216217041015625, 0.025360107421875, -0.04443359375,\n",
193+
" -0.029205322265625, -0.002414703369140625, 0.027130126953125,\n",
194+
" 0.028961181640625, 0.078857421875, -0.0009660720825195312,\n",
195+
" 0.017608642578125, 0.05755615234375, -0.0285797119140625,\n",
196+
" 0.0039215087890625, -0.006908416748046875, -0.05364990234375,\n",
197+
" -0.01342010498046875, -0.0247802734375, 0.08331298828125,\n",
198+
" 0.032928466796875, 0.00543975830078125, -0.0168304443359375,\n",
199+
" -0.050018310546875, -0.05908203125, 0.031951904296875,\n",
200+
" -0.0200347900390625, 0.019134521484375, -0.018035888671875,\n",
201+
" -0.01178741455078125\n",
202+
"]\n"
203+
]
204+
}
205+
],
206+
"source": [
207+
"const singleVector = await embeddings.embedQuery(text);\n",
208+
"\n",
209+
"console.log(singleVector.slice(0, 100));"
210+
]
211+
},
212+
{
213+
"cell_type": "markdown",
214+
"id": "1b5a7d03",
215+
"metadata": {},
216+
"source": [
217+
"### Embed multiple texts\n",
218+
"\n",
219+
"You can embed multiple texts for indexing with `embedDocuments`. The internals used for this method may (but do not have to) differ from embedding queries:"
220+
]
221+
},
222+
{
223+
"cell_type": "code",
224+
"execution_count": 4,
225+
"id": "2f4d6e97",
226+
"metadata": {},
227+
"outputs": [
228+
{
229+
"name": "stdout",
230+
"output_type": "stream",
231+
"text": [
232+
"[\n",
233+
" 0.016632080078125, 0.01165008544921875, -0.1181640625,\n",
234+
" -0.10186767578125, 0.05438232421875, -0.08905029296875,\n",
235+
" -0.0180511474609375, 0.00957489013671875, -0.08056640625,\n",
236+
" -0.0283203125, -0.0151214599609375, 0.0311279296875,\n",
237+
" 0.08184814453125, 0.0225982666015625, 0.0012750625610351562,\n",
238+
" 0.01336669921875, -0.043365478515625, -0.004322052001953125,\n",
239+
" -0.02410888671875, -0.0012559890747070312, -0.046356201171875,\n",
240+
" 0.0298919677734375, -0.013458251953125, -0.03765869140625,\n",
241+
" 0.07672119140625, 0.0217132568359375, 0.0179290771484375,\n",
242+
" -0.0002269744873046875, -0.0582275390625, -0.0224609375,\n",
243+
" 0.002834320068359375, -0.0174407958984375, -0.01512908935546875,\n",
244+
" -0.01146697998046875, -0.055206298828125, -0.08404541015625,\n",
245+
" 0.0567626953125, -0.0033092498779296875, -0.034271240234375,\n",
246+
" 0.05108642578125, -0.010101318359375, 0.046173095703125,\n",
247+
" 0.0011806488037109375, 0.005706787109375, 0.06854248046875,\n",
248+
" 0.0079193115234375, -0.0176239013671875, 0.002552032470703125,\n",
249+
" 0.059539794921875, -0.06573486328125, -0.07537841796875,\n",
250+
" -0.02484130859375, -0.027740478515625, 0.003925323486328125,\n",
251+
" 0.0263671875, 0.0660400390625, 0.0156402587890625,\n",
252+
" 0.033050537109375, -0.047821044921875, -0.0333251953125,\n",
253+
" 0.050445556640625, 0.07757568359375, -0.045257568359375,\n",
254+
" 0.07586669921875, 0.0021724700927734375, 0.0237274169921875,\n",
255+
" -0.052703857421875, 0.050323486328125, -0.0274658203125,\n",
256+
" -0.0024662017822265625, 0.0194244384765625, -0.03802490234375,\n",
257+
" 0.02166748046875, 0.025360107421875, -0.044464111328125,\n",
258+
" -0.0292816162109375, -0.0025119781494140625, 0.0271148681640625,\n",
259+
" 0.028961181640625, 0.078857421875, -0.0008907318115234375,\n",
260+
" 0.017669677734375, 0.0576171875, -0.0285797119140625,\n",
261+
" 0.0039825439453125, -0.00687408447265625, -0.0535888671875,\n",
262+
" -0.0134735107421875, -0.0247650146484375, 0.0831298828125,\n",
263+
" 0.032989501953125, 0.005443572998046875, -0.0167999267578125,\n",
264+
" -0.050018310546875, -0.059051513671875, 0.0318603515625,\n",
265+
" -0.0200958251953125, 0.0191192626953125, -0.0180206298828125,\n",
266+
" -0.01175689697265625\n",
267+
"]\n",
268+
"[\n",
269+
" -0.02667236328125, 0.036651611328125, -0.1630859375,\n",
270+
" -0.0904541015625, -0.022430419921875, -0.095458984375,\n",
271+
" -0.037628173828125, 0.00473785400390625, -0.046051025390625,\n",
272+
" 0.0109710693359375, 0.0113525390625, 0.0254364013671875,\n",
273+
" 0.09368896484375, 0.0144195556640625, -0.007564544677734375,\n",
274+
" -0.0014705657958984375, -0.0007691383361816406, -0.015716552734375,\n",
275+
" -0.0242156982421875, -0.024871826171875, 0.00885009765625,\n",
276+
" 0.0012922286987304688, 0.023712158203125, -0.054595947265625,\n",
277+
" 0.06329345703125, 0.0289306640625, 0.0233612060546875,\n",
278+
" -0.0374755859375, -0.0489501953125, -0.029510498046875,\n",
279+
" 0.0173492431640625, 0.0171356201171875, -0.01629638671875,\n",
280+
" -0.0352783203125, -0.039398193359375, -0.11138916015625,\n",
281+
" 0.0296783447265625, -0.01467132568359375, 0.0009188652038574219,\n",
282+
" 0.048187255859375, -0.010650634765625, 0.03125,\n",
283+
" 0.005214691162109375, -0.015869140625, 0.06939697265625,\n",
284+
" -0.0428466796875, 0.0266571044921875, 0.044189453125,\n",
285+
" 0.049957275390625, -0.054290771484375, 0.0107574462890625,\n",
286+
" -0.03265380859375, -0.0109100341796875, -0.0144805908203125,\n",
287+
" 0.03936767578125, 0.07989501953125, -0.056976318359375,\n",
288+
" 0.0308380126953125, -0.035125732421875, -0.038848876953125,\n",
289+
" 0.10748291015625, 0.01129150390625, -0.0665283203125,\n",
290+
" 0.09710693359375, 0.03143310546875, -0.0104522705078125,\n",
291+
" -0.062469482421875, 0.021148681640625, -0.00970458984375,\n",
292+
" -0.06756591796875, 0.01019287109375, 0.00433349609375,\n",
293+
" 0.032928466796875, 0.020233154296875, -0.01336669921875,\n",
294+
" -0.015472412109375, -0.0175933837890625, -0.0142364501953125,\n",
295+
" -0.007450103759765625, 0.03759765625, 0.003551483154296875,\n",
296+
" 0.0069580078125, 0.042266845703125, -0.007488250732421875,\n",
297+
" 0.01922607421875, 0.007080078125, -0.0255889892578125,\n",
298+
" -0.007686614990234375, -0.0848388671875, 0.058563232421875,\n",
299+
" 0.021148681640625, 0.034393310546875, 0.01087188720703125,\n",
300+
" -0.0196380615234375, -0.09515380859375, 0.0054931640625,\n",
301+
" -0.012481689453125, 0.003322601318359375, -0.019683837890625,\n",
302+
" -0.0307159423828125\n",
303+
"]\n"
304+
]
305+
}
306+
],
307+
"source": [
308+
"const text2 = \"LangGraph is a library for building stateful, multi-actor applications with LLMs\";\n",
309+
"\n",
310+
"const vectors = await embeddings.embedDocuments([text, text2]);\n",
311+
"\n",
312+
"console.log(vectors[0].slice(0, 100));\n",
313+
"console.log(vectors[1].slice(0, 100));"
314+
]
315+
},
316+
{
317+
"cell_type": "markdown",
318+
"id": "8938e581",
319+
"metadata": {},
320+
"source": [
321+
"## API reference\n",
322+
"\n",
323+
"For detailed documentation of all FireworksEmbeddings features and configurations head to the API reference: https://api.js.langchain.com/classes/langchain_community_embeddings_fireworks.FireworksEmbeddings.html"
324+
]
325+
}
326+
],
327+
"metadata": {
328+
"kernelspec": {
329+
"display_name": "Deno",
330+
"language": "typescript",
331+
"name": "deno"
332+
},
333+
"language_info": {
334+
"file_extension": ".ts",
335+
"mimetype": "text/x.typescript",
336+
"name": "typescript",
337+
"nb_converter": "script",
338+
"pygments_lexer": "typescript",
339+
"version": "5.3.3"
340+
}
341+
},
342+
"nbformat": 4,
343+
"nbformat_minor": 5
344+
}

‎docs/core_docs/docs/integrations/text_embedding/fireworks.mdx

-29
This file was deleted.

0 commit comments

Comments
 (0)