add audio streaming & pdf examples (#483)

* add audio streaming * Add pdf examples * Update samples/rest/text_generation.sh * remove test.pdf Change-Id: Icadde0849a0d358b605e7cfe6ff208d49d639dfb * use alt=sse for all streaming examples Change-Id: I6ee214edcc06827d1e73f7c1fdd3e380e7988896 --------- Co-authored-by: Mark Daoust <markdaoust@google.com>
google-gemini · Jul 23, 2024 · 695ee95 · 695ee95
1 parent f8b049f
commit 695ee95
Show file tree

Hide file tree

Showing 2 changed files with 158 additions and 7 deletions.
diff --git a/samples/rest/chat.sh b/samples/rest/chat.sh
@@ -25,7 +25,7 @@ curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:ge
 
 echo "[START chat_streaming]"
 # [START chat_streaming]
-curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?key=$GOOGLE_API_KEY \
+curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY \
     -H 'Content-Type: application/json' \
     -X POST \
     -d '{
@@ -53,7 +53,7 @@ else
   B64FLAGS="-w0"
 fi
 
-curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?key=$GOOGLE_API_KEY \
+curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY \
     -H 'Content-Type: application/json' \
     -X POST \
     -d '{

diff --git a/samples/rest/text_generation.sh b/samples/rest/text_generation.sh
@@ -6,15 +6,16 @@ MEDIA_DIR=$(realpath ${SCRIPT_DIR}/../../third_party)
 IMG_PATH=${MEDIA_DIR}/organ.jpg
 AUDIO_PATH=${MEDIA_DIR}/sample.mp3
 VIDEO_PATH=${MEDIA_DIR}/Big_Buck_Bunny.mp4
-
-BASE_URL="https://generativelanguage.googleapis.com"
+PDF_PATH=${MEDIA_DIR}/test.pdf
 
 if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
   B64FLAGS="--input"
 else
   B64FLAGS="-w0"
 fi
 
+BASE_URL="https://generativelanguage.googleapis.com"
+
 echo "[START text_gen_text_only_prompt]"
 # [START text_gen_text_only_prompt]
 curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
@@ -57,7 +58,7 @@ curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:g
 
 echo "[START text_gen_multimodal_one_image_prompt_streaming]"
 # [START text_gen_multimodal_one_image_prompt_streaming]
-curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?key=$GOOGLE_API_KEY" \
+curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY" \
     -H 'Content-Type: application/json' \
     -X POST \
     -d '{
@@ -125,6 +126,54 @@ echo
 jq ".candidates[].content.parts[].text" response.json
 # [END text_gen_multimodal_audio]
 
+echo "[START text_gen_multimodal_audio_streaming]"
+# [START text_gen_multimodal_audio_streaming]
+# Use File API to upload audio data to API request.
+MIME_TYPE=$(file -b --mime-type "${AUDIO_PATH}")
+NUM_BYTES=$(wc -c < "${AUDIO_PATH}")
+DISPLAY_NAME=AUDIO
+
+tmp_header_file=upload-header.tmp
+
+# Initial resumable request defining metadata.
+# The upload url is in the response headers dump them to a file.
+curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
+  -D upload-header.tmp \
+  -H "X-Goog-Upload-Protocol: resumable" \
+  -H "X-Goog-Upload-Command: start" \
+  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
+  -H "Content-Type: application/json" \
+  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null
+
+upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
+rm "${tmp_header_file}"
+
+# Upload the actual bytes.
+curl "${upload_url}" \
+  -H "Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Offset: 0" \
+  -H "X-Goog-Upload-Command: upload, finalize" \
+  --data-binary "@${AUDIO_PATH}" 2> /dev/null > file_info.json
+
+file_uri=$(jq ".file.uri" file_info.json)
+echo file_uri=$file_uri
+
+curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY" \
+    -H 'Content-Type: application/json' \
+    -X POST \
+    -d '{
+      "contents": [{
+        "parts":[
+          {"text": "Please describe this file."},
+          {"file_data":{"mime_type": "audio/mpeg", "file_uri": '$file_uri'}}]
+        }]
+       }' 2> /dev/null > response.json
+
+cat response.json
+echo
+# [END text_gen_multimodal_audio_streaming]
+
 echo "[START text_gen_multimodal_video_prompt]"
 # [START text_gen_multimodal_video_prompt]
 # Use File API to upload audio data to API request.
@@ -231,7 +280,7 @@ do
   state=$(jq ".file.state" file_info.json)
 done
 
-curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?key=$GOOGLE_API_KEY" \
+curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY" \
     -H 'Content-Type: application/json' \
     -X POST \
     -d '{
@@ -244,4 +293,106 @@ curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:s
 
 cat response.json
 echo
-# [END text_gen_multimodal_video_prompt_streaming]
+# [END text_gen_multimodal_video_prompt_streaming]
+
+echo "[START text_gen_multimodal_pdf]"
+# [START text_gen_multimodal_pdf]
+MIME_TYPE=$(file -b --mime-type "${PDF_PATH}")
+NUM_BYTES=$(wc -c < "${PDF_PATH}")
+DISPLAY_NAME=TEXT
+
+
+echo $MIME_TYPE
+tmp_header_file=upload-header.tmp
+
+# Initial resumable request defining metadata.
+# The upload url is in the response headers dump them to a file.
+curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
+  -D upload-header.tmp \
+  -H "X-Goog-Upload-Protocol: resumable" \
+  -H "X-Goog-Upload-Command: start" \
+  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
+  -H "Content-Type: application/json" \
+  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null
+
+upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
+rm "${tmp_header_file}"
+
+# Upload the actual bytes.
+curl "${upload_url}" \
+  -H "Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Offset: 0" \
+  -H "X-Goog-Upload-Command: upload, finalize" \
+  --data-binary "@${PDF_PATH}" 2> /dev/null > file_info.json
+
+file_uri=$(jq ".file.uri" file_info.json)
+echo file_uri=$file_uri
+
+# Now generate content using that file
+curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
+    -H 'Content-Type: application/json' \
+    -X POST \
+    -d '{
+      "contents": [{
+        "parts":[
+          {"text": "Can you add a few more lines to this poem?"},
+          {"file_data":{"mime_type": "application/pdf", "file_uri": '$file_uri'}}]
+        }]
+       }' 2> /dev/null > response.json
+
+cat response.json
+echo
+
+jq ".candidates[].content.parts[].text" response.json
+# [END text_gen_multimodal_pdf]
+
+echo "[START text_gen_multimodal_pdf_streaming]"
+# [START text_gen_multimodal_pdf_streaming]
+MIME_TYPE=$(file -b --mime-type "${PDF_PATH}")
+NUM_BYTES=$(wc -c < "${PDF_PATH}")
+DISPLAY_NAME=TEXT
+
+
+echo $MIME_TYPE
+tmp_header_file=upload-header.tmp
+
+# Initial resumable request defining metadata.
+# The upload url is in the response headers dump them to a file.
+curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
+  -D upload-header.tmp \
+  -H "X-Goog-Upload-Protocol: resumable" \
+  -H "X-Goog-Upload-Command: start" \
+  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
+  -H "Content-Type: application/json" \
+  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null
+
+upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
+rm "${tmp_header_file}"
+
+# Upload the actual bytes.
+curl "${upload_url}" \
+  -H "Content-Length: ${NUM_BYTES}" \
+  -H "X-Goog-Upload-Offset: 0" \
+  -H "X-Goog-Upload-Command: upload, finalize" \
+  --data-binary "@${PDF_PATH}" 2> /dev/null > file_info.json
+
+file_uri=$(jq ".file.uri" file_info.json)
+echo file_uri=$file_uri
+
+# Now generate content using that file
+curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=$GOOGLE_API_KEY" \
+    -H 'Content-Type: application/json' \
+    -X POST \
+    -d '{
+      "contents": [{
+        "parts":[
+          {"text": "Can you add a few more lines to this poem?"},
+          {"file_data":{"mime_type": "application/pdf", "file_uri": '$file_uri'}}]
+        }]
+       }' 2> /dev/null > response.json
+
+cat response.json
+echo
+# [END text_gen_multimodal_pdf_streaming]