From 254fea19d2d931da2429f46fe2ce4c878317e0a3 Mon Sep 17 00:00:00 2001 From: theanupllm <theanupdas@protonmail.com> Date: Thu, 2 May 2024 12:41:47 +0530 Subject: [PATCH] optimize logs --- docs/00-introduction.ipynb | 92 +++++------------------------- semantic_router/encoders/openai.py | 4 +- 2 files changed, 17 insertions(+), 79 deletions(-) diff --git a/docs/00-introduction.ipynb b/docs/00-introduction.ipynb index d03a09ff..209aa103 100644 --- a/docs/00-introduction.ipynb +++ b/docs/00-introduction.ipynb @@ -63,7 +63,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [ { @@ -100,7 +100,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -127,7 +127,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -155,36 +155,14 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger local\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 1 length: 34\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 1 trunc length: 34\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 2 length: 51\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 2 trunc length: 51\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 3 length: 33\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 3 trunc length: 33\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 4 length: 33\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 4 trunc length: 33\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 5 length: 38\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 5 trunc length: 38\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 6 length: 27\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 6 trunc length: 27\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 7 length: 24\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 7 trunc length: 24\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 8 length: 21\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 8 trunc length: 21\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 9 length: 20\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 9 trunc length: 20\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 10 length: 25\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 10 trunc length: 25\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 11 length: 22\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:30 INFO semantic_router.utils.logger Document 11 trunc length: 22\u001b[0m\n" + "\u001b[32m2024-05-02 12:38:34 INFO semantic_router.utils.logger local\u001b[0m\n" ] } ], @@ -203,24 +181,16 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[32m2024-05-02 12:09:35 INFO semantic_router.utils.logger Document 1 length: 24\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:35 INFO semantic_router.utils.logger Document 1 trunc length: 24\u001b[0m\n" - ] - }, { "data": { "text/plain": [ "RouteChoice(name='politics', function_call=None, similarity_score=None)" ] }, - "execution_count": 7, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -231,24 +201,16 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[32m2024-05-02 12:09:37 INFO semantic_router.utils.logger Document 1 length: 24\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:37 INFO semantic_router.utils.logger Document 1 trunc length: 24\u001b[0m\n" - ] - }, { "data": { "text/plain": [ "RouteChoice(name='chitchat', function_call=None, similarity_score=None)" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -266,24 +228,16 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[32m2024-05-02 12:09:38 INFO semantic_router.utils.logger Document 1 length: 40\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:38 INFO semantic_router.utils.logger Document 1 trunc length: 40\u001b[0m\n" - ] - }, { "data": { "text/plain": [ "RouteChoice(name=None, function_call=None, similarity_score=None)" ] }, - "execution_count": 9, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -301,17 +255,9 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[32m2024-05-02 12:09:40 INFO semantic_router.utils.logger Document 1 length: 35\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:40 INFO semantic_router.utils.logger Document 1 trunc length: 35\u001b[0m\n" - ] - }, { "data": { "text/plain": [ @@ -319,7 +265,7 @@ " RouteChoice(name='chitchat', function_call=None, similarity_score=0.8356239688161808)]" ] }, - "execution_count": 10, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -330,24 +276,16 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[32m2024-05-02 12:09:42 INFO semantic_router.utils.logger Document 1 length: 40\u001b[0m\n", - "\u001b[32m2024-05-02 12:09:42 INFO semantic_router.utils.logger Document 1 trunc length: 40\u001b[0m\n" - ] - }, { "data": { "text/plain": [ "[]" ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } diff --git a/semantic_router/encoders/openai.py b/semantic_router/encoders/openai.py index 3cfa2a70..1e647890 100644 --- a/semantic_router/encoders/openai.py +++ b/semantic_router/encoders/openai.py @@ -80,9 +80,9 @@ class OpenAIEncoder(BaseEncoder): if truncate: # check if any document exceeds token limit and truncate if so for i in range(len(docs)): - logger.info(f"Document {i+1} length: {len(docs[i])}") + # logger.info(f"Document {i+1} length: {len(docs[i])}") docs[i] = self._truncate(docs[i]) - logger.info(f"Document {i+1} trunc length: {len(docs[i])}") + # logger.info(f"Document {i+1} trunc length: {len(docs[i])}") # Exponential backoff for j in range(1, 7): -- GitLab