Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Google integrations: change answers to replies #216

Merged
merged 1 commit into from
Mar 27, 2024
Merged

Google integrations: change answers to replies #216

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions integrations/google-ai.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ os.environ["GOOGLE_API_KEY"] = "YOUR-GOOGLE-API-KEY"

gemini_generator = GoogleAIGeminiGenerator(model="gemini-pro")
result = gemini_generator.run(parts = ["What is assemblage in art?"])
print(result["answers"][0])
print(result["replies"][0])
```

Output:
Expand Down Expand Up @@ -103,7 +103,7 @@ os.environ["GOOGLE_API_KEY"] = "YOUR-GOOGLE-API-KEY"

gemini_generator = GoogleAIGeminiGenerator(model="gemini-pro-vision")
result = gemini_generator.run(parts = ["What can you tell me about these robots?", *images])
for answer in result["answers"]:
for answer in result["replies"]:
print(answer)
```

Expand Down Expand Up @@ -189,7 +189,7 @@ os.environ["GOOGLE_API_KEY"] = "YOUR-GOOGLE-API-KEY"

gemini_generator = GoogleAIGeminiGenerator(model="gemini-pro")
result = gemini_generator.run("Write a code for calculating fibonacci numbers in JavaScript")
print(result["answers"][0])
print(result["replies"][0])
```

Output:
Expand Down
14 changes: 7 additions & 7 deletions integrations/google-vertex-ai.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ from haystack_integrations.components.generators.google_vertex import VertexAIGe

gemini_generator = VertexAIGeminiGenerator(model="gemini-pro", project_id=project_id)
result = gemini_generator.run(parts = ["What is assemblage in art?"])
print(result["answers"][0])
print(result["replies"][0])
```
Output:
```shell
Expand Down Expand Up @@ -101,7 +101,7 @@ images = [
]
gemini_generator = VertexAIGeminiGenerator(model="gemini-pro-vision", project_id=project_id)
result = gemini_generator.run(parts = ["What can you tell me about these robots?", *images])
for answer in result["answers"]:
for answer in result["replies"]:
print(answer)
```
Output:
Expand Down Expand Up @@ -130,7 +130,7 @@ palm_llm_result = palm_llm.run(
Text: Google Pixel 7, 5G network, 8GB RAM, Tensor G2 processor, 128GB of storage, Lemongrass
JSON:
""")
print(palm_llm_result["answers"][0])
print(palm_llm_result["replies"][0])
```

### Codey API Models
Expand All @@ -144,7 +144,7 @@ from haystack_integrations.components.generators.google_vertex import VertexAICo

codey_llm = VertexAICodeGenerator(model="code-bison", project_id=project_id)
codey_llm_result = codey_llm.run("Write a code for calculating fibonacci numbers in JavaScript")
print(codey_llm_result["answers"][0])
print(codey_llm_result["replies"][0])
```

Here'a an example of using `code-gecko` model for **code completion**:
Expand All @@ -159,7 +159,7 @@ codey_llm_result = codey_llm.run("""function fibonacci(n) {
return n;
}
""")
print(codey_llm_result["answers"][0])
print(codey_llm_result["replies"][0])
```

### Imagen API models
Expand Down Expand Up @@ -201,7 +201,7 @@ print(image_captioner_result["captions"])

**Visual Question Answering (VQA) with `imagetext`**

To answers questions about an image, initialize a VertexAIImageQA with the `imagetext` model and `project_id`. Then, you can run it with the `image` and the `question`:
To answer questions about an image, initialize a VertexAIImageQA with the `imagetext` model and `project_id`. Then, you can run it with the `image` and the `question`:

```python
from haystack.dataclasses.byte_stream import ByteStream
Expand All @@ -213,5 +213,5 @@ image = ByteStream.from_file_path("output.png") # you can use the generated imag
question = "what's the color of the furniture?"

visual_qa_result = visual_qa.run(image=image,question=question)
print(visual_qa_result["answers"])
print(visual_qa_result["replies"])
```