Spaces:
Sleeping
Sleeping
Created using Colab
Browse files
notebooks/05-Improve_Prompts_+_Add_Source.ipynb
CHANGED
@@ -21,18 +21,73 @@
|
|
21 |
},
|
22 |
{
|
23 |
"cell_type": "code",
|
24 |
-
"execution_count":
|
25 |
"metadata": {
|
26 |
-
"
|
|
|
|
|
|
|
|
|
27 |
},
|
28 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"source": [
|
30 |
"!pip install -q llama-index==0.10.9 openai==1.12.0 tiktoken==0.6.0 chromadb==0.4.22 llama-index-vector-stores-chroma==0.1.7"
|
31 |
]
|
32 |
},
|
33 |
{
|
34 |
"cell_type": "code",
|
35 |
-
"execution_count":
|
36 |
"metadata": {
|
37 |
"id": "riuXwpSPcvWC"
|
38 |
},
|
@@ -41,12 +96,12 @@
|
|
41 |
"import os\n",
|
42 |
"\n",
|
43 |
"# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
|
44 |
-
"os.environ[\"OPENAI_API_KEY\"] = \"
|
45 |
]
|
46 |
},
|
47 |
{
|
48 |
"cell_type": "code",
|
49 |
-
"execution_count":
|
50 |
"metadata": {
|
51 |
"id": "km-KQOrgr3VB"
|
52 |
},
|
@@ -70,7 +125,7 @@
|
|
70 |
},
|
71 |
{
|
72 |
"cell_type": "code",
|
73 |
-
"execution_count":
|
74 |
"metadata": {
|
75 |
"id": "SQP87lHczHKc"
|
76 |
},
|
@@ -86,7 +141,7 @@
|
|
86 |
},
|
87 |
{
|
88 |
"cell_type": "code",
|
89 |
-
"execution_count":
|
90 |
"metadata": {
|
91 |
"id": "zAaGcYMJzHAN"
|
92 |
},
|
@@ -127,22 +182,22 @@
|
|
127 |
},
|
128 |
{
|
129 |
"cell_type": "code",
|
130 |
-
"execution_count":
|
131 |
"metadata": {
|
132 |
"colab": {
|
133 |
"base_uri": "https://localhost:8080/"
|
134 |
},
|
135 |
"id": "fQtpDvUzKNzI",
|
136 |
-
"outputId": "
|
137 |
},
|
138 |
"outputs": [
|
139 |
{
|
140 |
-
"name": "stdout",
|
141 |
"output_type": "stream",
|
|
|
142 |
"text": [
|
143 |
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
|
144 |
" Dload Upload Total Spent Left Speed\n",
|
145 |
-
"100 169k 100 169k 0 0
|
146 |
]
|
147 |
}
|
148 |
],
|
@@ -161,24 +216,24 @@
|
|
161 |
},
|
162 |
{
|
163 |
"cell_type": "code",
|
164 |
-
"execution_count":
|
165 |
"metadata": {
|
166 |
"colab": {
|
167 |
"base_uri": "https://localhost:8080/"
|
168 |
},
|
169 |
"id": "_WER5lt0N7c5",
|
170 |
-
"outputId": "
|
171 |
},
|
172 |
"outputs": [
|
173 |
{
|
|
|
174 |
"data": {
|
175 |
"text/plain": [
|
176 |
"14"
|
177 |
]
|
178 |
},
|
179 |
-
"execution_count": 7,
|
180 |
"metadata": {},
|
181 |
-
"
|
182 |
}
|
183 |
],
|
184 |
"source": [
|
@@ -209,7 +264,7 @@
|
|
209 |
},
|
210 |
{
|
211 |
"cell_type": "code",
|
212 |
-
"execution_count":
|
213 |
"metadata": {
|
214 |
"id": "lFvW_886dxKX"
|
215 |
},
|
@@ -223,30 +278,58 @@
|
|
223 |
},
|
224 |
{
|
225 |
"cell_type": "code",
|
226 |
-
"execution_count":
|
227 |
"metadata": {
|
228 |
"colab": {
|
229 |
"base_uri": "https://localhost:8080/"
|
230 |
},
|
231 |
"id": "Njoc3XEVkKkf",
|
232 |
-
"outputId": "
|
233 |
},
|
234 |
"outputs": [
|
235 |
{
|
|
|
236 |
"data": {
|
237 |
"text/plain": [
|
238 |
"14"
|
239 |
]
|
240 |
},
|
241 |
-
"execution_count": 9,
|
242 |
"metadata": {},
|
243 |
-
"
|
244 |
}
|
245 |
],
|
246 |
"source": [
|
247 |
"len( documents )"
|
248 |
]
|
249 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
{
|
251 |
"cell_type": "markdown",
|
252 |
"metadata": {
|
|
|
21 |
},
|
22 |
{
|
23 |
"cell_type": "code",
|
24 |
+
"execution_count": 1,
|
25 |
"metadata": {
|
26 |
+
"colab": {
|
27 |
+
"base_uri": "https://localhost:8080/"
|
28 |
+
},
|
29 |
+
"id": "QPJzr-I9XQ7l",
|
30 |
+
"outputId": "33a73316-fbb0-4ec8-e0ef-5f534108bb83"
|
31 |
},
|
32 |
+
"outputs": [
|
33 |
+
{
|
34 |
+
"output_type": "stream",
|
35 |
+
"name": "stdout",
|
36 |
+
"text": [
|
37 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m226.7/226.7 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
38 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
39 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m509.0/509.0 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
40 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m15.4/15.4 MB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
41 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m18.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
42 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
43 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
44 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
45 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m62.4/62.4 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
46 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m41.3/41.3 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
47 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m50.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
48 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m49.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
49 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m59.9/59.9 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
50 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m107.0/107.0 kB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
51 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
52 |
+
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
|
53 |
+
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
|
54 |
+
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
55 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m283.7/283.7 kB\u001b[0m \u001b[31m28.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
56 |
+
"\u001b[2K \u001b[90mβββββββββββββββββββββββββββββββββββοΏ½οΏ½οΏ½ββββ\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m64.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
57 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
58 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
59 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m53.6/53.6 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
60 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m142.5/142.5 kB\u001b[0m \u001b[31m16.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
61 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
62 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
63 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m141.9/141.9 kB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
64 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m290.4/290.4 kB\u001b[0m \u001b[31m27.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
65 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
66 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m52.5/52.5 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
67 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m130.5/130.5 kB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
68 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m29.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
69 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m48.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
70 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m61.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
71 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
72 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m307.7/307.7 kB\u001b[0m \u001b[31m32.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
73 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m47.2/47.2 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
74 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
75 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m49.3/49.3 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
76 |
+
"\u001b[?25h Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
77 |
+
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
|
78 |
+
"spacy 3.7.4 requires typer<0.10.0,>=0.3.0, but you have typer 0.12.3 which is incompatible.\n",
|
79 |
+
"weasel 0.3.4 requires typer<0.10.0,>=0.3.0, but you have typer 0.12.3 which is incompatible.\u001b[0m\u001b[31m\n",
|
80 |
+
"\u001b[0m"
|
81 |
+
]
|
82 |
+
}
|
83 |
+
],
|
84 |
"source": [
|
85 |
"!pip install -q llama-index==0.10.9 openai==1.12.0 tiktoken==0.6.0 chromadb==0.4.22 llama-index-vector-stores-chroma==0.1.7"
|
86 |
]
|
87 |
},
|
88 |
{
|
89 |
"cell_type": "code",
|
90 |
+
"execution_count": 2,
|
91 |
"metadata": {
|
92 |
"id": "riuXwpSPcvWC"
|
93 |
},
|
|
|
96 |
"import os\n",
|
97 |
"\n",
|
98 |
"# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
|
99 |
+
"os.environ[\"OPENAI_API_KEY\"] = \"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\"\n"
|
100 |
]
|
101 |
},
|
102 |
{
|
103 |
"cell_type": "code",
|
104 |
+
"execution_count": 3,
|
105 |
"metadata": {
|
106 |
"id": "km-KQOrgr3VB"
|
107 |
},
|
|
|
125 |
},
|
126 |
{
|
127 |
"cell_type": "code",
|
128 |
+
"execution_count": 4,
|
129 |
"metadata": {
|
130 |
"id": "SQP87lHczHKc"
|
131 |
},
|
|
|
141 |
},
|
142 |
{
|
143 |
"cell_type": "code",
|
144 |
+
"execution_count": 5,
|
145 |
"metadata": {
|
146 |
"id": "zAaGcYMJzHAN"
|
147 |
},
|
|
|
182 |
},
|
183 |
{
|
184 |
"cell_type": "code",
|
185 |
+
"execution_count": 6,
|
186 |
"metadata": {
|
187 |
"colab": {
|
188 |
"base_uri": "https://localhost:8080/"
|
189 |
},
|
190 |
"id": "fQtpDvUzKNzI",
|
191 |
+
"outputId": "96a94167-ec27-4cf7-abc2-1017ad01afac"
|
192 |
},
|
193 |
"outputs": [
|
194 |
{
|
|
|
195 |
"output_type": "stream",
|
196 |
+
"name": "stdout",
|
197 |
"text": [
|
198 |
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
|
199 |
" Dload Upload Total Spent Left Speed\n",
|
200 |
+
"100 169k 100 169k 0 0 302k 0 --:--:-- --:--:-- --:--:-- 302k\n"
|
201 |
]
|
202 |
}
|
203 |
],
|
|
|
216 |
},
|
217 |
{
|
218 |
"cell_type": "code",
|
219 |
+
"execution_count": 7,
|
220 |
"metadata": {
|
221 |
"colab": {
|
222 |
"base_uri": "https://localhost:8080/"
|
223 |
},
|
224 |
"id": "_WER5lt0N7c5",
|
225 |
+
"outputId": "fdf45169-f6c1-4e73-a476-3fb5e1adcd39"
|
226 |
},
|
227 |
"outputs": [
|
228 |
{
|
229 |
+
"output_type": "execute_result",
|
230 |
"data": {
|
231 |
"text/plain": [
|
232 |
"14"
|
233 |
]
|
234 |
},
|
|
|
235 |
"metadata": {},
|
236 |
+
"execution_count": 7
|
237 |
}
|
238 |
],
|
239 |
"source": [
|
|
|
264 |
},
|
265 |
{
|
266 |
"cell_type": "code",
|
267 |
+
"execution_count": 8,
|
268 |
"metadata": {
|
269 |
"id": "lFvW_886dxKX"
|
270 |
},
|
|
|
278 |
},
|
279 |
{
|
280 |
"cell_type": "code",
|
281 |
+
"execution_count": 9,
|
282 |
"metadata": {
|
283 |
"colab": {
|
284 |
"base_uri": "https://localhost:8080/"
|
285 |
},
|
286 |
"id": "Njoc3XEVkKkf",
|
287 |
+
"outputId": "5f270e74-465e-4252-e158-9a66e250cca4"
|
288 |
},
|
289 |
"outputs": [
|
290 |
{
|
291 |
+
"output_type": "execute_result",
|
292 |
"data": {
|
293 |
"text/plain": [
|
294 |
"14"
|
295 |
]
|
296 |
},
|
|
|
297 |
"metadata": {},
|
298 |
+
"execution_count": 9
|
299 |
}
|
300 |
],
|
301 |
"source": [
|
302 |
"len( documents )"
|
303 |
]
|
304 |
},
|
305 |
+
{
|
306 |
+
"cell_type": "code",
|
307 |
+
"source": [
|
308 |
+
"documents[0].metadata"
|
309 |
+
],
|
310 |
+
"metadata": {
|
311 |
+
"id": "lKaZYB_IPr62",
|
312 |
+
"outputId": "4b7083a3-bde2-4f5f-ab76-a5b5074484a8",
|
313 |
+
"colab": {
|
314 |
+
"base_uri": "https://localhost:8080/"
|
315 |
+
}
|
316 |
+
},
|
317 |
+
"execution_count": 12,
|
318 |
+
"outputs": [
|
319 |
+
{
|
320 |
+
"output_type": "execute_result",
|
321 |
+
"data": {
|
322 |
+
"text/plain": [
|
323 |
+
"{'title': \"Beyond GPT-4: What's New?\",\n",
|
324 |
+
" 'url': 'https://pub.towardsai.net/beyond-gpt-4-whats-new-cbd61a448eb9#dda8',\n",
|
325 |
+
" 'source_name': 'towards_ai'}"
|
326 |
+
]
|
327 |
+
},
|
328 |
+
"metadata": {},
|
329 |
+
"execution_count": 12
|
330 |
+
}
|
331 |
+
]
|
332 |
+
},
|
333 |
{
|
334 |
"cell_type": "markdown",
|
335 |
"metadata": {
|